Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 102492
    Prev
    Next
    INDEX
    Explanations

    references to "view" in code or documentation contexts

    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
     Schindler
    -0.52
    sct
    -0.52
     RCMP
    -0.51
    stridium
    -0.51
     Albright
    -0.50
     Hornets
    -0.50
     McCormack
    -0.50
     Malone
    -0.49
     Kessler
    -0.48
     Alban
    -0.48
    POSITIVE LOGITS
     View
    1.40
    view
    1.33
     view
    1.32
     VIEW
    1.30
    View
    1.30
    VIEW
    1.16
     Views
    1.02
     views
    1.00
     VIEWS
    0.96
    getView
    0.91
    Activations Density 0.033%

    No Known Activations