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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 51710
    Prev
    Next
    INDEX
    Explanations

    elements of schema and structure in code or data formats

    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
     ब्रेकडाउन
    -0.39
     ligiloj
    -0.35
     hell
    -0.35
    endpush
    -0.34
     cycle
    -0.34
     prazo
    -0.33
    AnimationsModule
    -0.32
    Jpa
    -0.32
     ciclo
    -0.30
     ep
    -0.29
    POSITIVE LOGITS
     OFDb
    0.72
    HostException
    0.70
    Autoritní
    0.63
    verwijspagina
    0.57
    CodeAttribute
    0.57
     мәкал
    0.55
    WithIOException
    0.55
    تقاوى
    0.52
     utafitiHapana
    0.52
    RTLI
    0.52
    Activations Density 0.123%

    No Known Activations