© 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. 14468
    Prev
    Next
    INDEX
    Explanations

    the presence of structured data or sequences within written content

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

    Grammatical sentence endings

    np_acts-logits-general · gemini-2.0-flash

    end of sentence 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
    \<^
    -1.71
    >\<^
    -1.71
    NUMX
    -1.68
    )";
    -1.61
     $_"
    -1.58
    ^(@)
    -1.57
     ་་
    -1.54
    '},
    -1.52
    )");
    -1.47
     }}$}
    -1.46
    POSITIVE LOGITS
    <eos>
    1.71
    ↵
    1.34
    ↵↵
    1.18
    ...
    1.12
    http
    1.10
    …
    1.09
    I
    1.08
    https
    1.06
    A
    1.04
     -
    1.03
    Activations Density 1.241%

    No Known Activations