© 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. 4778
    Prev
    Next
    INDEX
    Explanations

    references to configuration files and related parameters in code or system settings

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

    configuration or config-related terms in technical source code or programming contexts.

    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
     MainAxisSize
    -0.67
     FontWeight
    -0.48
    <bos>
    -0.48
    male
    -0.47
     venons
    -0.46
    RTSC
    -0.45
    MethodManager
    -0.45
     Abel
    -0.45
    last
    -0.44
    WA
    -0.43
    POSITIVE LOGITS
     config
    1.13
     Config
    1.06
     configuration
    1.05
    config
    1.01
     CONFIG
    0.98
    Config
    0.97
     Configuration
    0.95
     getConfig
    0.95
     configurations
    0.92
    getConfig
    0.89
    Activations Density 0.063%

    No Known Activations