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

    Neuronpedia

    Jacobian LensNEW
    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. 4871
    Prev
    Next
    INDEX
    Explanations

    elements of logical expressions and mathematical representations in data

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

    Code, assertions, or colons

    np_acts-logits-general · gemini-2.0-flash

    variable assignment or definition

    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
    UBA
    -0.53
    taku
    -0.51
    Gavin
    -0.50
     Hew
    -0.49
     Stacey
    -0.49
    ultu
    -0.48
     Sarmiento
    -0.47
     Taw
    -0.47
     Buchanan
    -0.47
     Femen
    -0.46
    POSITIVE LOGITS
    (":
    0.98
    =:
    0.97
    ,:
    0.95
     ":
    0.95
    (':
    0.94
     ':
    0.93
    :=
    0.92
    .:
    0.92
    /:
    0.90
    ::
    0.89
    Activations Density 0.299%

    No Known Activations