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. 91635
    Prev
    Next
    INDEX
    Explanations

    comment syntax 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
    principalTable
    -0.57
    RenderAtEndOf
    -0.52
    onOptions
    -0.47
    parsedMessage
    -0.42
    UseVisualStyle
    -0.40
    BeginInit
    -0.39
    StartTag
    -0.38
    MigrationBuilder
    -0.38
     media
    -0.37
    __["
    -0.37
    POSITIVE LOGITS
     ușor
    0.49
     Exacts
    0.45
    ➊
    0.45
     <<<<<<<<<<<<<<
    0.44
    makeText
    0.44
     nødven
    0.44
     uș
    0.43
    Unlike
    0.43
    ifrance
    0.43
     inappropriés
    0.42
    Activations Density 0.024%

    No Known Activations