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. 26783
    Prev
    Next
    INDEX
    Explanations

    technical terms related to web development or HTTP requests

    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
     joining
    -0.31
    ljen
    -0.30
     senior
    -0.29
    isTrue
    -0.29
     출
    -0.29
     Schutz
    -0.29
     '@/
    -0.29
    Increment
    -0.28
     कह
    -0.28
     prestations
    -0.28
    POSITIVE LOGITS
     FormData
    3.70
    FormData
    1.16
     formData
    0.98
    Autoritní
    0.82
     PeEnEo
    0.72
    formData
    0.70
    rungsseite
    0.68
    UrlEncoded
    0.68
    ChildScrollView
    0.67
     ProtoMessage
    0.66
    Activations Density 0.000%

    No Known Activations