© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 15156
    Prev
    Next
    INDEX
    Explanations

    references to "classic" items or themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    providedIn
    -0.77
    oncesto
    -0.73
    SBATCH
    -0.71
    Искәрмәләр
    -0.70
     SqlParameter
    -0.69
     VIAF
    -0.68
    hoots
    -0.67
     benessere
    -0.66
    Referencie
    -0.66
    DispatchToProps
    -0.66
    POSITIVE LOGITS
     classic
    1.99
    classic
    1.96
     Classic
    1.91
     classics
    1.87
    Classic
    1.86
     CLASSIC
    1.85
     Classics
    1.80
     klasik
    1.63
     clásicos
    1.57
     classique
    1.56
    Activations Density 0.035%

    No Known Activations