© 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. 27922
    Prev
    Next
    INDEX
    Explanations

    references to previously described methods or protocols in scientific texts

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

    previously described methods

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Tikang
    -0.44
     autorytatywna
    -0.39
    WebMethod
    -0.33
     tortas
    -0.33
     للاسماء
    -0.33
    bewerken
    -0.32
    DeleteMapping
    -0.31
    GEBURTSDATUM
    -0.30
    Translatef
    -0.30
     noDo
    -0.30
    POSITIVE LOGITS
    存于互联网档案馆
    0.54
     previously
    0.53
    parsedMessage
    0.51
    ioneers
    0.49
    careous
    0.47
    berdayakan
    0.47
     previous
    0.47
    announced
    0.46
     dezelve
    0.46
    previously
    0.46
    Activations Density 0.453%

    No Known Activations