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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 12718
    Prev
    Next
    INDEX
    Explanations

    elements related to LaTeX document formatting and package usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.40
    DispatchToProps
    -0.40
    createServer
    -0.37
    GoogleApiClient
    -0.36
    ValueGeneration
    -0.34
    withIdentifier
    -0.32
    knex
    -0.31
    TintMode
    -0.29
     πέ
    -0.29
    penup
    -0.29
    POSITIVE LOGITS
    amssymb
    0.60
     Administrativna
    0.57
     AssemblyCulture
    0.56
    BibitemShut
    0.56
     חיצוניים
    0.55
     ARXIV
    0.52
    bibfield
    0.51
    DotNetBar
    0.51
    bernate
    0.50
    >';
    0.50
    Activations Density 0.172%

    No Known Activations