© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10235
    Prev
    Next
    INDEX
    Explanations

    terms related to states of being or conditions that are not functioning as intended

    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
    RuleContext
    -0.51
     M
    -0.48
    posis
    -0.47
    CGRectMake
    -0.46
     Ge
    -0.46
     T
    -0.45
    T
    -0.44
     SwiftUI
    -0.43
     vo
    -0.42
    opher
    -0.42
    POSITIVE LOGITS
     unprepared
    1.79
     unex
    1.66
     unsupported
    1.65
     untrained
    1.64
     unresolved
    1.63
     unqualified
    1.61
     untreated
    1.55
     unre
    1.55
     undetected
    1.54
     undis
    1.52
    Activations Density 0.077%

    No Known Activations