© 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-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 2222
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly in a biographical or contextual setting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    msgTypes
    -0.51
    expandindo
    -0.50
    jsdelivr
    -0.48
    zzleHttp
    -0.46
     ويكيميديا
    -0.43
    ۣ
    -0.43
    ScopeManager
    -0.43
     때문
    -0.42
    allos
    -0.41
    orsese
    -0.41
    POSITIVE LOGITS
     passed
    0.96
     beloved
    0.87
     formerly
    0.82
     died
    0.79
     Passed
    0.78
     resident
    0.76
    Passed
    0.74
    Beloved
    0.73
     departed
    0.72
     longtime
    0.72
    Activations Density 0.134%

    No Known Activations