© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7054
    Prev
    Next
    INDEX
    Explanations

    structured data and parameters related to computing resources and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical computing parameters and configuration settings, particularly related to memory, cache, and system configurations.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    compound technical identifiers for configuration or metrics (often camelCase or underscore-separated) in code or config, frequently near numeric values.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    variable or parameter assignments in code, especially those involving numeric values or buffer sizes.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.82
    TypedDataSet
    -0.76
     للمعارف
    -0.72
     незавершена
    -0.69
     للاسماء
    -0.68
     protoimpl
    -0.68
    tagHelperRunner
    -0.67
     beſch
    -0.67
     CreateTagHelper
    -0.66
    GEBURTSDATUM
    -0.66
    POSITIVE LOGITS
     closely
    0.34
    /**
    0.31
    простра
    0.31
    �
    0.30
    ****************
    0.30
     slightly
    0.30
    čenje
    0.30
     reserves
    0.29
    <?
    0.29
    ksis
    0.29
    Activations Density 0.444%

    No Known Activations