© 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. 8495
    Prev
    Next
    INDEX
    Explanations

    symbols and mathematical notation

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

    Commas in mathematical or formal expressions

    np_acts-logits-general · gemini-2.0-flash

    lists of variables

    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
     createState
    -0.68
    "
    -0.67
    Искәрмәләр
    -0.57
     lenker
    -0.56
    ')))
    -0.56
    (
    -0.56
    Istorija
    -0.56
    ]";
    -0.56
    saraba
    -0.56
    '}}
    -0.52
    POSITIVE LOGITS
     ...,
    0.91
    _,
    0.84
     ?,
    0.75
     *,
    0.73
     etc
    0.73
    +,
    0.73
     ',',
    0.71
    =,
    0.70
    [],
    0.69
    ?,
    0.68
    Activations Density 0.371%

    No Known Activations