© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 408
    Prev
    Next
    INDEX
    Explanations

    references to programs or interventions in various contexts

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

    references to specific programs or initiatives

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

    program name and highlights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    EDEFAULT
    -0.89
    astify
    -0.83
     مشين
    -0.77
    DeleteBehavior
    -0.77
    AccessorTable
    -0.76
    AutoScaleMode
    -0.72
     تضيفلها
    -0.72
     TimeUnit
    -0.70
     Oxide
    -0.69
     XNUMX
    -0.69
    POSITIVE LOGITS
     programs
    1.19
     Programs
    1.07
    Programs
    1.05
    programs
    0.95
     programmes
    0.94
    matically
    0.94
     program
    0.91
    PROGRAM
    0.88
     PROGRAMS
    0.87
     progra
    0.85
    Activations Density 0.027%

    No Known Activations