© 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. 9-GEMMASCOPE-RES-16K
    11. 14377
    Prev
    Next
    INDEX
    Explanations

    expressions related to technical specifications and conditions

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

    items in numbered or lettered lists, particularly when formatted with parentheses like (1), (2), (3) or (a), (b), (c).

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    auw
    -0.56
    ReusableCell
    -0.48
    DOCTYPE
    -0.47
    signol
    -0.44
    AtIndexPath
    -0.44
     Rek
    -0.43
    InMillis
    -0.43
    uldig
    -0.43
     tiens
    -0.43
    CHREIBUNG
    -0.43
    POSITIVE LOGITS
     ProtoMessage
    0.52
     reaſon
    0.46
    stylers
    0.45
    intios
    0.44
    InputTagHelper
    0.43
     continúas
    0.40
     Wikimedijinoj
    0.39
    addCriterion
    0.38
     reafon
    0.36
     gyhoeddwyd
    0.36
    Activations Density 0.732%

    No Known Activations