© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 4034
    Prev
    Next
    INDEX
    Explanations

    conditional and probabilistic phrases related to events or outcomes

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

    almost surely

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fflush
    -0.28
    baiki
    -0.24
     Gesamt
    -0.23
     ninguna
    -0.23
    Andere
    -0.22
    None
    -0.22
     Andere
    -0.22
    何より
    -0.21
     ninguno
    -0.21
     vieta
    -0.21
    POSITIVE LOGITS
     almost
    2.91
    almost
    2.80
     nearly
    2.61
    Almost
    2.58
     practically
    2.58
     Almost
    2.55
     virtually
    2.53
     quase
    2.52
    nearly
    2.39
     hampir
    2.34
    Activations Density 0.263%

    No Known Activations