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

    Neuronpedia

    Jacobian LensNEW
    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 - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 10793
    Prev
    Next
    INDEX
    Explanations

    statements about expected behaviors in expressions and function-related constructs

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    tagHelperRunner
    -1.28
     Efq
    -1.20
    RenderAtEndOf
    -1.12
    évaluateur
    -1.03
     Reſ
    -1.03
     Monfieur
    -1.02
     myſelf
    -1.02
    OGND
    -0.99
     purpoſe
    -0.99
     Eſ
    -0.98
    POSITIVE LOGITS
    Expression
    0.76
    Should
    0.71
     Will
    0.69
     
    0.66
     expression
    0.64
     (
    0.64
    ,
    0.63
      
    0.61
     Should
    0.59
    Will
    0.59
    Activations Density 0.179%

    No Known Activations