© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 9927
    Prev
    Next
    INDEX
    Explanations

    specific terms related to withdrawal or retraction, particularly in a medical or procedural context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ">//
    -0.85
    +:+
    -0.77
    出版年
    -0.66
    ///</
    -0.64
     дописавши
    -0.61
    >({
    -0.60
    HasAnnotation
    -0.58
     Tee
    -0.57
     mash
    -0.55
     cross
    -0.54
    POSITIVE LOGITS
    apollo
    0.75
    السكان
    0.73
     Thunderbolt
    0.72
    unculus
    0.68
     apollo
    0.68
     turkeys
    0.66
     Nimbus
    0.66
     bekend
    0.66
     Hercules
    0.66
     Aquarius
    0.66
    Activations Density 0.062%

    No Known Activations