© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 39262
    Prev
    Next
    INDEX
    Explanations

    attributes and functions related to visibility in UI elements

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

    visibility state in code

    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
    empereur
    -0.46
    Monte
    -0.37
     döv
    -0.37
    tså
    -0.36
    étape
    -0.36
     romántica
    -0.36
     macchine
    -0.35
    Empereur
    -0.35
     romantique
    -0.35
     Macs
    -0.35
    POSITIVE LOGITS
    visibility
    2.72
    Visibility
    2.44
     Visibility
    2.41
     visibility
    2.31
     visibilidad
    1.66
     visibilité
    1.62
    setVisibility
    1.59
     VIS
    1.20
    VIS
    1.15
     visible
    1.13
    Activations Density 0.003%

    No Known Activations