Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6618
    Prev
    Next
    INDEX
    Explanations

    structures related to timing and sequencing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ViewImports
    -0.46
    parsedMessage
    -0.44
    UrlResolution
    -0.43
    basicConfig
    -0.43
     disambiguazione
    -0.42
    twimg
    -0.42
    IsUnicode
    -0.41
     nargin
    -0.40
    DJANGO
    -0.40
    writerow
    -0.40
    POSITIVE LOGITS
     Sobald
    1.02
     sobald
    0.90
     Dès
    0.69
    Once
    0.69
     Once
    0.68
    Dès
    0.62
    once
    0.59
     dès
    0.56
    Upon
    0.53
     once
    0.53
    Activations Density 0.191%

    No Known Activations