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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 80221
    Prev
    Next
    INDEX
    Explanations

    references to official documents and records related to companies and financial accounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    ftagPool
    -0.53
    lickr
    -0.43
    featureID
    -0.34
    WireFormatLite
    -0.34
    putExtra
    -0.32
    permitAll
    -0.31
     ISNI
    -0.30
    泵
    -0.30
     takich
    -0.30
    IsContent
    -0.29
    POSITIVE LOGITS
     nakalista
    0.69
     disambiguazione
    0.56
    허
    0.54
    Business
    0.48
    ArrowToggle
    0.47
    ViewImports
    0.47
    rawValue
    0.46
     registered
    0.45
    sidemargin
    0.45
     Walkover
    0.44
    Activations Density 0.058%

    No Known Activations