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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-GEMMASCOPE-RES-131K
    6. 1247
    Prev
    Next
    INDEX
    Explanations

    references to the Bootstrap framework and its CDN links

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    web resource urls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     financières
    -0.35
     její
    -0.35
     őket
    -0.34
     okolí
    -0.34
     étrangers
    -0.33
     aprovechar
    -0.33
     fritas
    -0.32
    日閲覧
    -0.32
     bertindak
    -0.31
     comunión
    -0.31
    POSITIVE LOGITS
    bootstrapcdn
    1.60
    twimg
    1.36
    findpost
    1.23
    imageshack
    1.09
    +#+
    1.05
    ftagPool
    0.99
    photobucket
    0.95
    TagMode
    0.94
    jsdelivr
    0.93
    usercontent
    0.92
    Activations Density 0.032%

    No Known Activations