© 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. 18-GEMMASCOPE-RES-16K
    11. 15143
    Prev
    Next
    INDEX
    Explanations

    instances of dialogue or reported speech

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

    Preceding a pronoun (he/him/his)

    np_acts-logits-general · gemini-2.0-flash

    he, him, his pronoun usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدیا
    -0.95
    tagHelperRunner
    -0.92
     initComponents
    -0.91
     Efq
    -0.88
    endphp
    -0.87
    +#+#
    -0.84
     ویکی‌پدیای
    -0.83
    RenderAtEndOf
    -0.83
     ſeveral
    -0.83
    AnchorStyles
    -0.82
    POSITIVE LOGITS
     Mr
    0.57
     him
    0.57
     通販
    0.53
    (
    0.50
     he
    0.49
    はじめに
    0.48
    Mr
    0.47
    *
    0.44
     او
    0.43
    ^
    0.42
    Activations Density 0.631%

    No Known Activations