© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14132
    Prev
    Next
    INDEX
    Explanations

    technical terms related to dynamic systems and their evaluations

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

    technical conditions or logical statements in scientific or programming text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.58
     AspNetCore
    -0.54
     auroit
    -0.52
    findpost
    -0.52
    CPtr
    -0.50
     typelib
    -0.49
     strijd
    -0.48
     Geſch
    -0.48
     Prüf
    -0.48
     disambiguazione
    -0.48
    POSITIVE LOGITS
    BufferException
    0.46
    getItemId
    0.42
    WebApplication
    0.36
    المناصب
    0.36
    AndEndTag
    0.35
    曖昧さ回避
    0.35
    Välislingid
    0.35
    ValuePair
    0.35
     Stable
    0.33
    addPreferredGap
    0.32
    Activations Density 1.120%

    No Known Activations