Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 6831
    Prev
    Next
    INDEX
    Explanations

    references to time and the analysis of it 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 @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Púb
    -0.69
     InkWell
    -0.66
    LLocation
    -0.61
    WebServlet
    -0.61
    addGap
    -0.60
    addContainerGap
    -0.57
     Exactly
    -0.54
    aarrggbb
    -0.52
     exactly
    -0.50
    iseite
    -0.50
    POSITIVE LOGITS
    through
    0.78
     through
    0.70
    THROUGH
    0.69
     Bourgoin
    0.67
    Through
    0.66
     través
    0.64
     Through
    0.63
     attraverso
    0.61
    henswürdigkeiten
    0.61
     através
    0.60
    Activations Density 0.096%

    No Known Activations