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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 17390
    Prev
    Next
    INDEX
    Explanations

    references to "Razor" and related terms

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

    Razorbacks

    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
     mellem
    -0.31
    jdons
    -0.29
    Zwischen
    -0.28
     ronda
    -0.27
     jūsų
    -0.27
     between
    -0.26
     valmis
    -0.25
    й
    -0.25
     niech
    -0.25
    enumi
    -0.25
    POSITIVE LOGITS
    Razor
    2.80
     Razor
    2.23
    razor
    1.83
     razor
    1.68
     RAZ
    1.23
    RAZ
    1.05
    ScopeManager
    1.00
     Raz
    0.95
     raz
    0.95
    Raz
    0.94
    Activations Density 0.000%

    No Known Activations