© 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. 9-GEMMASCOPE-RES-131K
    6. 17412
    Prev
    Next
    INDEX
    Explanations

    elements related to statistical measures or numerical data

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

    timestamps and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.57
     autorytatywna
    -0.54
     zijne
    -0.54
    arangay
    -0.53
     INTERESAR
    -0.52
     afecto
    -0.52
     viajeros
    -0.52
     estabilidad
    -0.51
    adesivo
    -0.51
    adap
    -0.51
    POSITIVE LOGITS
    0
    0.76
    OO
    0.65
     OO
    0.62
    oo
    0.55
    Hoo
    0.51
     Goo
    0.50
    Goo
    0.49
     Nee
    0.47
     Oo
    0.47
    setNum
    0.46
    Activations Density 0.174%

    No Known Activations