© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 12915
    Prev
    Next
    INDEX
    Explanations

    terms related to crime, fraud, and specific services offered by companies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     חיצוניים
    -0.65
     ProtoMessage
    -0.62
    Билгалдахарш
    -0.59
     Seeder
    -0.58
     kaynağından
    -0.58
    principalColumn
    -0.56
    berikut
    -0.55
    
    -0.54
     necessária
    -0.53
     adequada
    -0.53
    POSITIVE LOGITS
     mainly
    0.91
    主に
    0.82
     primarily
    0.82
     specializes
    0.82
     mostly
    0.80
    mainly
    0.78
     specializing
    0.76
     specialize
    0.73
     specialises
    0.72
     specialising
    0.71
    Activations Density 0.263%

    No Known Activations