© 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. 64435
    Prev
    Next
    INDEX
    Explanations

    names of individuals

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

    biographies of people

    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
    хьтан
    -0.79
    Autoritní
    -0.76
    Jeografia
    -0.73
    +#+
    -0.71
    uxxxx
    -0.66
    msgTypes
    -0.66
     ویکی‌پدی
    -0.66
    angliski
    -0.65
     Мексичка
    -0.63
     betweenstory
    -0.63
    POSITIVE LOGITS
     himself
    0.58
     kimdir
    0.56
     who
    0.46
     esprits
    0.45
     Kecil
    0.44
     appunto
    0.43
     cristiano
    0.40
     couverts
    0.37
     özg
    0.36
     cristiana
    0.36
    Activations Density 0.031%

    No Known Activations