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
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 5902
    Prev
    Next
    INDEX
    Explanations

    terms related to optical features and security measures in currency and other documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ProtoMessage
    -0.68
    
    -0.65
    LookAnd
    -0.63
    setVerticalGroup
    -0.60
     AssemblyTitle
    -0.58
    rungsseite
    -0.58
    
    -0.57
    bootstrapcdn
    -0.56
     незавершена
    -0.54
    withIdentifier
    -0.53
    POSITIVE LOGITS
     shimmering
    0.31
     viewed
    0.31
     sheen
    0.30
     mesmerizing
    0.26
    chaft
    0.26
    Eksteraj
    0.25
     iridescent
    0.25
     mój
    0.25
     pigments
    0.25
    cjach
    0.25
    Activations Density 0.505%

    No Known Activations