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-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 772
    Prev
    Next
    INDEX
    Explanations

    references to maintenance and repair services in technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.48
    protoc
    -0.48
    stdc
    -0.47
    __(/*!
    -0.47
     HttpNotFound
    -0.44
    tagHelperRunner
    -0.44
     Pfeffer
    -0.44
     Gestaltung
    -0.43
    atase
    -0.42
    EndContext
    -0.41
    POSITIVE LOGITS
     repair
    2.39
     repairs
    2.27
     Repair
    2.15
    repair
    2.06
     repairing
    2.04
    Repair
    2.04
     Repairs
    2.00
     REPAIR
    1.94
     repaired
    1.93
     Reparatur
    1.62
    Activations Density 0.394%

    No Known Activations