© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4970
    Prev
    Next
    INDEX
    Explanations

    references to legal agreements and contracts that require documentation in writing

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

    "in writing" within license agreements

    np_acts-logits-general · gemini-2.0-flash

    in writing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     estekak
    -0.87
     Signalez
    -0.78
     defStyleAttr
    -0.71
    sizeCache
    -0.70
    adpleegd
    -0.68
     للاسماء
    -0.68
    клопе
    -0.67
     insuffisamment
    -0.67
    PreExecute
    -0.66
    DockStyle
    -0.66
    POSITIVE LOGITS
     written
    1.60
     writing
    1.40
     Written
    1.36
    written
    1.33
    Written
    1.30
     WRITTEN
    1.29
     escrito
    1.28
    writing
    1.22
     écrit
    1.20
     tertulis
    1.20
    Activations Density 0.221%

    No Known Activations