© 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. 22-GEMMASCOPE-RES-16K
    11. 12653
    Prev
    Next
    INDEX
    Explanations

    punctuation related to code syntax

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

    Code-related colons/symbols

    np_acts-logits-general · gemini-2.0-flash

    class definitions and scientific terms

    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
    /
    -0.52
    -&
    -0.49
    ();*/
    -0.49
     otherwise
    -0.48
    \/
    -0.48
    =\"
    -0.47
    ten
    -0.47
    bel
    -0.47
    <h6>
    -0.46
    arti
    -0.46
    POSITIVE LOGITS
     propOrder
    0.83
     الحره
    0.74
     <=",
    0.74
    ագրություններ
    0.72
    :✨
    0.72
    __":
    0.71
    PhysRevD
    0.71
     للاسماء
    0.70
    AccessorTable
    0.65
    paravant
    0.64
    Activations Density 0.030%

    No Known Activations