© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 93246
    Prev
    Next
    INDEX
    Explanations

    instances of uncertainty or ambiguity in discussions about evidence and legal proceedings

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

    assumptions or rules

    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
     endblock
    -0.75
     صوتيه
    -0.64
     Réponses
    -0.63
    GEBURTSDATUM
    -0.63
     otomatig
    -0.63
    AddTagHelper
    -0.60
    CloseOperation
    -0.59
     Administrativna
    -0.59
    Personendaten
    -0.57
    URLException
    -0.56
    POSITIVE LOGITS
    and
    0.84
    as
    0.81
    at
    0.79
    or
    0.77
    is
    0.76
    the
    0.76
    un
    0.75
    in
    0.75
    to
    0.75
    pro
    0.75
    Activations Density 0.478%

    No Known Activations