© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 6846
    Prev
    Next
    INDEX
    Explanations

    the presence of the suffix "ful" in words

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

    gainful activity

    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
     initComponents
    -0.61
    Примітки
    -0.55
     Petersen
    -0.54
     Infórmanos
    -0.54
    endregion
    -0.53
     estadounid
    -0.53
    Παραπομπές
    -0.53
     houſe
    -0.52
    TextAppearance
    -0.52
     contextLoads
    -0.51
    POSITIVE LOGITS
    ful
    2.89
    FUL
    2.20
    Ful
    1.72
     ful
    1.57
    fuls
    1.55
     Ful
    1.48
    fulness
    1.43
     FUL
    1.39
    full
    1.26
    eful
    1.13
    Activations Density 0.003%

    No Known Activations