© 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. 19-GEMMASCOPE-RES-16K
    11. 3247
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to exercise and fitness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.67
    jspx
    -0.61
    rawDesc
    -0.60
    DotNetBar
    -0.57
    ंदीखरीदारी
    -0.55
    Datuak
    -0.55
    RUnlock
    -0.55
    DoubleQuotes
    -0.55
    EndContext
    -0.55
    ScopeManager
    -0.54
    POSITIVE LOGITS
     fitness
    2.14
     gym
    2.09
     workout
    1.99
     Fitness
    1.94
     Gym
    1.82
     gyms
    1.82
    Fitness
    1.81
    fitness
    1.80
    gym
    1.74
     exercise
    1.73
    Activations Density 0.159%

    No Known Activations