© 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. 13611
    Prev
    Next
    INDEX
    Explanations

    references to sphinx or sphincter-related terms

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

    sphinx and sphincter

    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
    BarItem
    -0.55
    天
    -0.44
     guy
    -0.40
     Gera
    -0.37
    day
    -0.37
     gehe
    -0.35
    tagHelperRunner
    -0.34
    <![
    -0.34
    styleType
    -0.33
     guys
    -0.33
    POSITIVE LOGITS
     Sphinx
    2.56
     sphinx
    2.41
    sphinx
    2.41
    phinx
    2.11
    sphin
    1.42
     Sph
    1.38
    Sph
    1.25
     sph
    1.20
     SPH
    1.16
    sph
    1.07
    Activations Density 0.005%

    No Known Activations