Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 32188
    Prev
    Next
    INDEX
    Explanations

    pronouns used to refer to individuals or groups

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

    we introduce, present, explain

    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
     wasn
    -0.72
     was
    -0.66
     has
    -0.65
     hasn
    -0.63
     lacked
    -0.57
    wasn
    -0.53
     is
    -0.50
     estaba
    -0.50
     wasnt
    -0.50
    cemment
    -0.48
    POSITIVE LOGITS
     take
    0.84
     make
    0.81
     get
    0.79
     give
    0.78
     create
    0.71
     provide
    0.69
     acquire
    0.68
     bring
    0.68
     decide
    0.68
     introduce
    0.68
    Activations Density 0.136%

    No Known Activations