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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 8783
    Prev
    Next
    INDEX
    Explanations

    structural elements and delimiters in programming code

    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
     tiro
    -0.30
    tät
    -0.29
     sép
    -0.28
     filepath
    -0.27
    beitet
    -0.27
    annelse
    -0.27
     parís
    -0.26
     civils
    -0.26
     metaphor
    -0.26
     Menteri
    -0.25
    POSITIVE LOGITS
    WithIOException
    0.69
    oredCriteria
    0.68
    XmlAccessType
    0.68
     Chwiliwch
    0.65
    ValueStyle
    0.65
     nakalista
    0.65
     Numerade
    0.64
     мәкал
    0.63
     EconPapers
    0.63
     ProtoMessage
    0.63
    Activations Density 0.074%

    No Known Activations