© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 13030
    Prev
    Next
    INDEX
    Explanations

    end curly braces or closing parentheses in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     оригіналу
    -0.60
     wako
    -0.53
     planks
    -0.52
    futbolista
    -0.52
    keit
    -0.51
    Sponsored
    -0.50
     Vek
    -0.49
     Screws
    -0.48
     mwenye
    -0.47
     ホイール
    -0.47
    POSITIVE LOGITS
     @"/
    0.72
     дописавши
    0.69
    IsContent
    0.68
    ]--;
    0.67
    ″]
    0.66
     endblock
    0.66
     AssemblyVersion
    0.64
    "]}
    0.63
    awtextra
    0.63
    qtype
    0.62
    Activations Density 0.088%

    No Known Activations