© 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. 94137
    Prev
    Next
    INDEX
    Explanations

    conditional statements and implications in mathematical contexts

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

    if... then... consequence

    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
     ostavi
    -0.65
    存于互联网档案馆
    -0.63
    Referències
    -0.59
    devamını
    -0.55
    OGND
    -0.52
    ViewFeatures
    -0.49
    ſelf
    -0.48
    قایناق‌لار
    -0.48
     kaarangay
    -0.48
     للاسماء
    -0.47
    POSITIVE LOGITS
    assertThat
    0.62
    此时
    0.48
     aguj
    0.47
     thì
    0.47
     فإن
    0.46
     pertanto
    0.46
    wherein
    0.45
    此時
    0.45
     sáb
    0.44
    jména
    0.44
    Activations Density 0.072%

    No Known Activations