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. 20-GEMMASCOPE-RES-16K
    6. 691
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to systems and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    webElementGuid
    -0.83
    sizeCache
    -0.79
    principalColumn
    -0.78
    fjspx
    -0.74
    InitVars
    -0.71
    rungsseite
    -0.68
    }])
    -0.67
    FunctionFlags
    -0.64
    InjectAttribute
    -0.64
     архивлан
    -0.64
    POSITIVE LOGITS
     proprement
    0.69
    providedIn
    0.66
    __;
    0.65
     stessi
    0.64
     automatiques
    0.61
     stessa
    0.60
     समीक्षाओं
    0.60
    seamnă
    0.59
     medes
    0.56
     skolan
    0.55
    Activations Density 2.380%

    No Known Activations