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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 75043
    Prev
    Next
    INDEX
    Explanations

    expressions of strong emotions and passionate viewpoints

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

    strong emotions and passion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.79
     kaarangay
    -0.77
    expandindo
    -0.73
    IntoConstraints
    -0.73
     otomatig
    -0.72
     HttpNotFound
    -0.71
    ſſung
    -0.71
     ſind
    -0.69
    <unused8>
    -0.68
    <unused28>
    -0.68
    POSITIVE LOGITS
     passionate
    0.85
     passionately
    0.83
     apasion
    0.76
     vehement
    0.69
     passion
    0.68
    assioned
    0.68
     intensity
    0.65
     vehemently
    0.64
     pasión
    0.63
     intensidad
    0.62
    Activations Density 0.021%

    No Known Activations