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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 68955
    Prev
    Next
    INDEX
    Explanations

    instances of executable files

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

    executable files and dlls

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    mybatisplus
    -0.68
     يتيمه
    -0.59
    AccessorTable
    -0.57
     المعيارى
    -0.56
     disponibilités
    -0.55
     Infórmanos
    -0.54
    httphttps
    -0.52
     nahilalakip
    -0.51
    addCriterion
    -0.50
    ScopeManager
    -0.50
    POSITIVE LOGITS
    exe
    1.02
    Exe
    0.86
    EXE
    0.76
     exe
    0.72
     EXE
    0.69
     Exe
    0.63
     executable
    0.49
    esez
    0.49
     sessionId
    0.49
     screenWidth
    0.47
    Activations Density 0.004%

    No Known Activations