© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 4057
    Prev
    Next
    INDEX
    Explanations

    the structure and syntax of code blocks or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cestershire
    -0.58
    +#+
    -0.56
    reactstrap
    -0.55
    Specificity
    -0.54
    ⓧ
    -0.54
    frontmatter
    -0.53
    cinogenicity
    -0.52
    versiti
    -0.51
    rawDesc
    -0.51
    EDEFAULT
    -0.51
    POSITIVE LOGITS
     snippetHide
    0.62
    (!__
    0.59
     Drapeau
    0.55
     AssemblyTitle
    0.54
    findpost
    0.53
     ModelExpression
    0.52
     StatefulWidget
    0.49
    endmodule
    0.49
     ecológica
    0.48
    TagMode
    0.48
    Activations Density 0.134%

    No Known Activations