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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 39035
    Prev
    Next
    INDEX
    Explanations

    references to containers or vessels used for cooking or holding substances

    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
     незавершена
    -0.94
    Referències
    -0.93
    nastics
    -0.91
    CloseOperation
    -0.86
    chenkt
    -0.86
    
    -0.84
    Джерела
    -0.84
     HasFactory
    -0.84
    ']],
    -0.83
    */].
    -0.82
    POSITIVE LOGITS
     Pot
    1.60
     pot
    1.57
    pot
    1.48
    Pot
    1.46
     POT
    1.45
     pots
    1.41
     Potts
    1.35
     Pots
    1.33
    POT
    1.32
     Potter
    1.13
    Activations Density 0.008%

    No Known Activations