© 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-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 64004
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to liability and negligence

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

    confirmation of cause or discretion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NOPQRST
    -0.58
    IntoConstraints
    -0.52
     FetchType
    -0.49
    UnusedPrivate
    -0.44
    tagHelperRunner
    -0.43
    aarrggbb
    -0.41
    principalColumn
    -0.40
    RectangleBorder
    -0.39
    AccessFile
    -0.39
     SDLK
    -0.38
    POSITIVE LOGITS
     exists
    1.34
     exist
    1.31
     Exists
    1.23
     existed
    1.19
     Exist
    1.16
    exists
    1.10
     EXISTS
    1.10
     EXIST
    1.09
     Existence
    1.09
    exist
    1.08
    Activations Density 0.368%

    No Known Activations