© 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. 8-GEMMASCOPE-RES-16K
    6. 6847
    Prev
    Next
    INDEX
    Explanations

    references to "classic" and "traditional" elements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    -1.11
    
    -1.05
    parsedMessage
    -0.99
     InputDecoration
    -0.99
     VIAF
    -0.95
    SBATCH
    -0.94
    SourceChecksum
    -0.89
    تقاوى
    -0.88
    AccessorTable
    -0.82
    Искәрмәләр
    -0.81
    POSITIVE LOGITS
     classics
    1.31
     classic
    1.25
    classic
    1.25
     Classic
    1.18
     klasik
    1.16
     traditional
    1.15
     tradition
    1.15
    Classic
    1.13
    traditional
    1.12
     traditions
    1.11
    Activations Density 0.134%

    No Known Activations