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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9524
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to "end" or "endocrine," often indicating finality or transitions in a biological context

    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
    StoryboardSegue
    -0.97
     ModelExpression
    -0.97
    URLException
    -0.96
    setVerticalGroup
    -0.94
     Lightboxes
    -0.88
    findpost
    -0.86
    Autoritní
    -0.83
    zzleHttp
    -0.83
    yntaxException
    -0.79
     дописавши
    -0.79
    POSITIVE LOGITS
     End
    0.67
     END
    0.62
    End
    0.62
     end
    0.60
     user
    0.57
    ToEnd
    0.53
     endgame
    0.51
    user
    0.51
    end
    0.49
     goal
    0.48
    Activations Density 0.118%

    No Known Activations