© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 8383
    Prev
    Next
    INDEX
    Explanations

    sections and headings within a document

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

    after asterisks/bolded tokens

    np_acts-logits-general · gemini-2.0-flash

    special characters introducing terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 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
    Wrk
    -0.44
     enfans
    -0.43
    rrggbb
    -0.40
    arraycopy
    -0.38
     Reck
    -0.37
    skjaer
    -0.36
    المكان
    -0.36
    usermodel
    -0.35
     voeten
    -0.35
     cenar
    -0.35
    POSITIVE LOGITS
     autorytatywna
    0.70
     ModelExpression
    0.59
    請繼續往下閱讀
    0.57
    ValueStyle
    0.56
    queryInterface
    0.50
     ExecuteAsync
    0.49
     typelib
    0.47
    Kariera
    0.47
     defaultstate
    0.47
     handling
    0.46
    Activations Density 0.238%

    No Known Activations