© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 93892
    Prev
    Next
    INDEX
    Explanations

    references to specific places or historical landmarks

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

    royal palace or Astronomical research

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    randomUUID
    -0.60
     оригіналу
    -0.59
    #+#
    -0.59
    parsedMessage
    -0.58
    ſelf
    -0.57
    TemporalType
    -0.56
    存于互联网档案馆
    -0.55
     Efq
    -0.54
    rophes
    -0.54
    UserScript
    -0.54
    POSITIVE LOGITS
    ercito
    0.40
    writeFieldEnd
    0.39
     padat
    0.35
     ddelweddau
    0.34
     ativa
    0.34
    huur
    0.33
     AttributeSet
    0.33
     puas
    0.32
     Hard
    0.32
     hard
    0.32
    Activations Density 0.068%

    No Known Activations