© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 11099
    Prev
    Next
    INDEX
    Explanations

    references to mirrors and reflective surfaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NSCoder
    -0.71
    expandindo
    -0.68
    BagConstraints
    -0.66
    yarnpkg
    -0.66
    enumii
    -0.64
    providedIn
    -0.64
    SharedDtor
    -0.64
    IsContent
    -0.62
    SharedCtor
    -0.62
    endpush
    -0.61
    POSITIVE LOGITS
     reflection
    2.98
     reflect
    2.72
     reflecting
    2.63
     reflected
    2.63
     reflections
    2.55
     reflective
    2.50
     mirror
    2.48
     Reflect
    2.45
     Reflection
    2.42
    reflect
    2.39
    Activations Density 0.526%

    No Known Activations