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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 9200
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

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

    comma punctuation, especially as separators within clauses or lists.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    commas that separate items in lists or clauses in technical and formal writing.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    “
    -0.54
    .”
    -0.48
    .
    -0.48
    ...
    -0.48
    :].
    -0.48
    "/>
    -0.47
    ‍
    -0.46
    }/>
    -0.45
    …
    -0.45
    .]
    -0.44
    POSITIVE LOGITS
     kasarigan
    0.85
    .$,
    0.80
    ⟬
    0.78
    =,
    0.75
     \%,
    0.73
    ,<
    0.72
    ₂,
    0.69
    awtextra
    0.68
     $,
    0.67
    \%,
    0.67
    Activations Density 2.785%

    No Known Activations