© 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. 18-GEMMASCOPE-RES-16K
    11. 3341
    Prev
    Next
    INDEX
    Explanations

    references to figures and data visuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "figure" or "figures"

    np_acts-logits-general · gemini-2.0-flash

    figure out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sortBy
    -0.55
     levé
    -0.52
    mailto
    -0.49
    cstdlib
    -0.49
     sleepers
    -0.48
    paper
    -0.48
     taboo
    -0.47
    Detal
    -0.46
    ConstraintMaker
    -0.46
     Vive
    -0.46
    POSITIVE LOGITS
     figures
    1.21
     Figures
    1.20
     Figure
    1.10
     figure
    1.10
    Figures
    1.09
     FIGURES
    1.09
     Figue
    1.00
    figures
    1.00
     FIGURE
    0.99
    figure
    0.95
    Activations Density 0.181%

    No Known Activations