© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6643
    Prev
    Next
    INDEX
    Explanations

    technical terms related to data structures and programming

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

    programming code parameters, specifically configuration-related syntax.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    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
     Administrativna
    -0.81
     Савезне
    -0.80
    MigrationBuilder
    -0.78
    XmlAccessorType
    -0.76
     CreateTagHelper
    -0.72
    GEBURTSDATUM
    -0.71
    WithIOException
    -0.70
    oa̍t
    -0.70
     ExecuteAsync
    -0.69
    transQ
    -0.68
    POSITIVE LOGITS
     also
    0.45
     likewise
    0.43
     ebenfalls
    0.39
     similarly
    0.38
     equally
    0.36
     fat
    0.35
     too
    0.35
     either
    0.35
     szint
    0.32
    WhereInput
    0.32
    Activations Density 0.515%

    No Known Activations