© 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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 57384
    Prev
    Next
    INDEX
    Explanations

    temporal references and previous time-related events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    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
    -0.61
    abestanden
    -0.58
    Искәрмәләр
    -0.56
     contactez
    -0.53
     ervan
    -0.52
     extinción
    -0.51
     mukana
    -0.51
    ]")]
    -0.50
     habet
    -0.50
     fortfarande
    -0.49
    POSITIVE LOGITS
     previous
    0.91
    previous
    0.77
     PREVIOUS
    0.76
     previously
    0.71
    Previous
    0.71
     prev
    0.70
     earlier
    0.69
     pasada
    0.69
     Previous
    0.69
    PREVIOUS
    0.68
    Activations Density 0.134%

    No Known Activations