© 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. 11073
    Prev
    Next
    INDEX
    Explanations

    references to various forms of light

    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
    oredCriteria
    -0.72
    InitVars
    -0.70
     betweenstory
    -0.69
     dAtA
    -0.69
    IntoConstraints
    -0.68
    PostInfinity
    -0.67
     GenerationType
    -0.66
    twimg
    -0.64
    transQ
    -0.62
    parsedMessage
    -0.60
    POSITIVE LOGITS
     Light
    0.73
    Light
    0.68
    bulb
    0.62
     LIGHT
    0.57
     light
    0.56
     bulb
    0.54
    LIGHT
    0.54
    hearted
    0.53
    light
    0.52
    NING
    0.46
    Activations Density 0.147%

    No Known Activations