© 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. 13260
    Prev
    Next
    INDEX
    Explanations

    phrases indicating secrecy and the act of preventing information from being disclosed

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

    not public or unreleased

    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
    CloseOperation
    -0.36
    arrings
    -0.35
     متعلقه
    -0.33
     poète
    -0.33
     comportement
    -0.33
     delegación
    -0.33
     position
    -0.33
    position
    -0.33
     dîner
    -0.33
    TintMode
    -0.32
    POSITIVE LOGITS
     offent
    0.74
     public
    0.69
     publicly
    0.65
     veřej
    0.65
     unreleased
    0.63
     published
    0.63
    公開
    0.62
     unpublished
    0.59
    published
    0.59
    seen
    0.59
    Activations Density 0.050%

    No Known Activations