Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 113556
    Prev
    Next
    INDEX
    Explanations

    references to curves and their characteristics in graphical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     National
    -0.47
     Niet
    -0.46
     Not
    -0.44
     Dos
    -0.44
    isNot
    -0.43
     PDR
    -0.43
    lao
    -0.42
     Second
    -0.42
    Not
    -0.42
    Dos
    -0.42
    POSITIVE LOGITS
    curve
    1.19
     curve
    1.18
    Curve
    1.11
     Curve
    1.09
     Curves
    0.91
     curves
    0.87
    curves
    0.86
     curva
    0.81
     courbe
    0.77
    Curves
    0.76
    Activations Density 0.008%

    No Known Activations