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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 16069
    Prev
    Next
    INDEX
    Explanations

    code imports and module references in programming languages

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

    Code, abbreviations, or website-related text

    np_acts-logits-general · gemini-2.0-flash

    from, site, etc

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.59
     архивлан
    -0.56
    IContainer
    -0.48
    (!__
    -0.44
    olah
    -0.44
    個
    -0.43
    weds
    -0.42
    ējās
    -0.42
     cakes
    -0.42
     PMA
    -0.42
    POSITIVE LOGITS
    httphttps
    0.85
    MENAFN
    0.74
     cref
    0.66
    Jeografia
    0.65
    ,:)
    0.64
     ".";
    0.64
    __(/*!
    0.63
     noqa
    0.60
     AssemblyTitle
    0.60
     Knowles
    0.59
    Activations Density 0.009%

    No Known Activations