© 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. 15438
    Prev
    Next
    INDEX
    Explanations

    terms related to various biological processes and properties

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

    Things that are shaped like something

    np_acts-logits-general · gemini-2.0-flash

    small individual items

    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
    RepeatedField
    -0.70
    setDo
    -0.66
    الحياه
    -0.65
    setVerticalGroup
    -0.64
    észet
    -0.61
    CodedInputStream
    -0.60
    anguages
    -0.59
     ModelExpression
    -0.59
     tetanus
    -0.56
    colhead
    -0.55
    POSITIVE LOGITS
     balls
    0.78
     miniature
    0.76
     tiny
    0.75
     viên
    0.74
     pill
    0.69
     ball
    0.68
     pills
    0.67
     Miniature
    0.67
    一个个
    0.65
     mini
    0.65
    Activations Density 0.654%

    No Known Activations