© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 1079
    Prev
    Next
    INDEX
    Explanations

    references to statistical significance in research findings

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    "p<0.00" followed by a digit

    np_acts-logits-general · gemini-2.0-flash

    statistical significance values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    তথ্যসূত্র
    -0.49
    pters
    -0.46
    NameInMap
    -0.45
     <=",
    -0.42
     HasFactory
    -0.42
    最快更新
    -0.41
    󠁿
    -0.41
    PhysRevD
    -0.39
    gdx
    -0.39
     simplifié
    -0.39
    POSITIVE LOGITS
    WebElementEntity
    0.56
    twimg
    0.43
    entuk
    0.41
    LookAnd
    0.41
    jenih
    0.40
     externi
    0.40
     MainAxisSize
    0.39
    Jereo
    0.39
     sente
    0.39
    izos
    0.38
    Activations Density 0.701%

    No Known Activations