© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 2001
    Prev
    Next
    INDEX
    Explanations

    numerical values and their contextual representations

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

    Numbers or formulas followed by numbers

    np_acts-logits-general · gemini-2.0-flash

    numbers and punctuation

    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
     single
    -0.46
    endregion
    -0.45
     тем
    -0.43
    perti
    -0.43
    #'
    -0.43
     ModelRenderer
    -0.43
    nem
    -0.41
    stackrel
    -0.41
    cı
    -0.40
    endfor
    -0.40
    POSITIVE LOGITS
    RenderAtEndOf
    0.84
    RegistryLite
    0.82
    LEncoder
    0.73
    __(/*!
    0.70
    脚注の使い方
    0.68
     doInBackground
    0.65
    migrationBuilder
    0.65
    ParallelGroup
    0.64
     surla
    0.64
    import
    0.63
    Activations Density 0.643%

    No Known Activations