© 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. 18-GEMMASCOPE-RES-16K
    11. 4161
    Prev
    Next
    INDEX
    Explanations

    specific formatting and layout attributes in code, particularly related to dimensions and positions

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

    Height or size specifications

    np_acts-logits-general · gemini-2.0-flash

    dimensions or size

    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
    AddHtmlAttribute
    -0.58
    RenderAtEndOf
    -0.53
     ivelany
    -0.52
     الاطلاع
    -0.46
    setattr
    -0.46
     Процитовано
    -0.45
    ::::::::
    -0.45
     TestBed
    -0.45
    <eos>
    -0.45
    wide
    -0.45
    POSITIVE LOGITS
     getHeight
    0.92
    Höhe
    0.73
     tallest
    0.73
     height
    0.69
    protoimpl
    0.68
    TypedDataSet
    0.68
     CURIAM
    0.68
     surla
    0.63
     hauteur
    0.63
     heights
    0.62
    Activations Density 0.165%

    No Known Activations