© 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-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 1722
    Prev
    Next
    INDEX
    Explanations

    patterns or sequences of numbers and their significance in a specific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ftagPool
    -0.86
    PerformLayout
    -0.78
     typelib
    -0.69
     Wikimedijinoj
    -0.62
    fieldId
    -0.62
     DbType
    -0.61
    enumii
    -0.59
    /*++
    -0.58
    gifs
    -0.58
    +:+
    -0.57
    POSITIVE LOGITS
    OGND
    0.52
    actionMode
    0.51
     Smy
    0.48
    TagHelpers
    0.48
    outSlope
    0.45
     Bohn
    0.44
    }');
    0.44
    Jenny
    0.44
     opri
    0.43
     Huy
    0.43
    Activations Density 0.064%

    No Known Activations