© 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. 20-GEMMASCOPE-RES-131K
    11. 21512
    Prev
    Next
    INDEX
    Explanations

    concepts related to openness and acceptance

    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
     فريبيس
    -0.54
    таратура
    -0.50
     Execution
    -0.48
     execution
    -0.45
     Stopwatch
    -0.45
     kasarigan
    -0.44
     executions
    -0.43
    guantes
    -0.43
    tierrez
    -0.43
    Watched
    -0.42
    POSITIVE LOGITS
     openness
    0.77
     open
    0.77
     opened
    0.71
    open
    0.70
    Open
    0.66
     terbuka
    0.66
     OPEN
    0.66
     ouverte
    0.65
     opens
    0.64
     ouvert
    0.64
    Activations Density 0.055%

    No Known Activations