© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 12161
    Prev
    Next
    INDEX
    Explanations

    terms related to allegations and accusations, particularly in legal or misconduct contexts

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

    allegations and accusations

    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
     OBSERV
    -0.36
    ắng
    -0.34
     JADX
    -0.32
     banks
    -0.32
     estratégica
    -0.32
     telo
    -0.31
    obs
    -0.31
    ⓧ
    -0.31
     intentionally
    -0.31
     spieg
    -0.30
    POSITIVE LOGITS
     allegations
    1.16
     accusations
    0.88
     allegation
    0.78
    alleg
    0.77
     claims
    0.72
    accus
    0.68
    Alleg
    0.68
     Alleg
    0.67
    ConstraintMaker
    0.66
    claims
    0.65
    Activations Density 0.050%

    No Known Activations