Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 51761
    Prev
    Next
    INDEX
    Explanations

    references to light conditions and their effects on visibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ControllerBase
    -0.56
    ſelf
    -0.48
     CURIAM
    -0.47
    providedIn
    -0.46
     CGRectMake
    -0.45
    เอง
    -0.44
     náz
    -0.43
     igång
    -0.43
    numerusform
    -0.42
     sentenza
    -0.41
    POSITIVE LOGITS
    hoeddwyd
    0.50
    XmlAccessType
    0.47
     NIGHT
    0.46
     night
    0.45
    InitVars
    0.44
     darkness
    0.44
    night
    0.43
     nighttime
    0.42
     Night
    0.40
     outdoor
    0.40
    Activations Density 0.016%

    No Known Activations