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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 23444
    Prev
    Next
    INDEX
    Explanations

    terms related to vehicle lighting technologies

    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
    ValueStyle
    -0.68
    AddTagHelper
    -0.66
     estekak
    -0.63
    TagMode
    -0.54
    ölkerung
    -0.53
    istoitu
    -0.53
     doInBackground
    -0.51
    TypedDataSet
    -0.49
    Loose
    -0.48
     Loose
    -0.47
    POSITIVE LOGITS
     headlights
    0.63
     headlight
    0.52
     headlamp
    0.50
     eyes
    0.43
     lanterns
    0.43
     lampu
    0.42
     eye
    0.40
    AnimationsModule
    0.39
     lights
    0.39
     Eye
    0.38
    Activations Density 0.003%

    No Known Activations