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. 8966
    Prev
    Next
    INDEX
    Explanations

    references to strips, particularly in a scientific or technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    strip contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     NavController
    -0.69
    tableFuture
    -0.65
    MemoryWarning
    -0.61
     Fonten
    -0.54
    Naissance
    -0.54
    onError
    -0.53
     fontSize
    -0.52
    QMetaType
    -0.52
     DbContext
    -0.52
    Gog
    -0.52
    POSITIVE LOGITS
     strip
    1.03
     Strip
    1.02
    strip
    0.99
     STRIP
    0.96
    Strip
    0.96
     strips
    0.87
     Strips
    0.84
     stripping
    0.79
     stripped
    0.71
    STRIP
    0.71
    Activations Density 0.010%

    No Known Activations