© 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. 3-GEMMASCOPE-RES-16K
    11. 9857
    Prev
    Next
    INDEX
    Explanations

    presence of a specific format or structure in code, particularly patterns of output or return values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    διά
    -0.53
     maternelle
    -0.52
    Blanc
    -0.51
    Süd
    -0.50
     TTT
    -0.50
    
    -0.49
     interest
    -0.48
     personnalité
    -0.47
    hors
    -0.47
    brain
    -0.47
    POSITIVE LOGITS
     AssemblyCulture
    0.85
    else
    0.85
    GOTREF
    0.77
     else
    0.77
    RetentionPolicy
    0.74
     تضيفلها
    0.69
    enumi
    0.69
    '||
    0.66
    HasAnnotation
    0.66
    elseif
    0.65
    Activations Density 0.062%

    No Known Activations