© 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. 18-GEMMASCOPE-RES-16K
    11. 512
    Prev
    Next
    INDEX
    Explanations

    technical terms related to scientific research and methodology

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

    Text following prepositions like "of" or "for."

    np_acts-logits-general · gemini-2.0-flash

    scientific and academic fields

    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
    IsMutable
    -0.62
     Lehre
    -0.57
    stateProvider
    -0.51
     en
    -0.45
    /\/
    -0.41
     thủ
    -0.40
    Superview
    -0.40
     at
    -0.39
    getMenuInflater
    -0.38
    /
    -0.38
    POSITIVE LOGITS
    tvguidetime
    0.78
     makeStyles
    0.72
    usermodel
    0.71
    出版年
    0.70
    -------
    0.69
    MLLoader
    0.69
    Trichloroethane
    0.69
    ConstraintMaker
    0.68
    Enllaces
    0.67
    poptosis
    0.67
    Activations Density 0.525%

    No Known Activations