© 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. 10-GEMMASCOPE-RES-16K
    11. 8611
    Prev
    Next
    INDEX
    Explanations

    references to negative or unfavorable qualities, particularly related to credit or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adaptiveStyles
    -0.95
    ViewFeatures
    -0.94
     Bourgoin
    -0.88
    DockStyle
    -0.87
     Laing
    -0.87
    GOTREF
    -0.86
    AndEndTag
    -0.86
    WireFormatLite
    -0.85
     copii
    -0.85
     useRouter
    -0.85
    POSITIVE LOGITS
     BAD
    1.68
     Bad
    1.67
     bad
    1.61
    Bad
    1.61
    bad
    1.55
    BAD
    1.47
     worse
    1.09
     Good
    1.04
    good
    1.03
     GOOD
    1.02
    Activations Density 0.040%

    No Known Activations