© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 9669
    Prev
    Next
    INDEX
    Explanations

    themes that evoke emotional complexity or explore various nuances in narratives and experiences

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

    as well as

    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
     therefore
    -0.56
    Improved
    -0.50
     Improved
    -0.49
     donc
    -0.48
     hence
    -0.47
     Therefore
    -0.47
     Increased
    -0.46
    SaveChangesAsync
    -0.45
     therefor
    -0.45
    Therefore
    -0.45
    POSITIVE LOGITS
     rarer
    1.01
     newer
    0.88
    更有
    0.81
    更为
    0.78
     simpler
    0.78
     broader
    0.77
     більш
    0.73
    更
    0.72
     bardziej
    0.72
     darker
    0.71
    Activations Density 0.129%

    No Known Activations