© 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. 97157
    Prev
    Next
    INDEX
    Explanations

    identifiers and variables related to programming and screen management

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

    screen capture and configuration `.screenrc`

    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
     المعيارى
    -0.57
    GEBURTSDATUM
    -0.48
    InteropServices
    -0.46
    zol
    -0.45
    inSlope
    -0.45
     pensieri
    -0.45
     segni
    -0.44
     infused
    -0.44
    SourceChecksum
    -0.44
    disposing
    -0.44
    POSITIVE LOGITS
     screen
    1.45
    screen
    1.36
     Screen
    1.33
    Screen
    1.32
     SCREEN
    1.27
     screens
    1.23
    SCREEN
    1.17
     Screens
    1.11
    screens
    1.03
    creen
    1.00
    Activations Density 0.015%

    No Known Activations