© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 5540
    Prev
    Next
    INDEX
    Explanations

    concepts related to evolutionary biology and species interaction

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

    Punctuation after certain words

    np_acts-logits-general · gemini-2.0-flash

    hyphenated or followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \{\\
    -1.09
    ."));
    -0.83
    :");
    -0.80
    (");
    -0.80
    。
    -0.79
     AssemblyCulture
    -0.76
    .");
    -0.75
    ...");
    -0.75
    lapsingToolbar
    -0.74
    '))
    -0.73
    POSITIVE LOGITS
     –
    2.66
     -
    2.64
     —
    2.57
     --
    2.42
    —
    2.13
     −
    1.96
    --
    1.87
    –
    1.81
     $-$
    1.76
     –,
    1.71
    Activations Density 0.878%

    No Known Activations