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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3313
    Prev
    Next
    INDEX
    Explanations

    phrases related to measurements of weight and mass

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    andoah
    -0.58
    InjectAttribute
    -0.54
     Paglinawan
    -0.52
     initComponents
    -0.47
    closePath
    -0.47
     Domenico
    -0.45
    ScopeManager
    -0.45
    nyder
    -0.44
     initWithFrame
    -0.44
     <=",
    -0.43
    POSITIVE LOGITS
     weight
    1.25
    weight
    1.16
    Weight
    1.09
     Weight
    1.05
     weights
    1.05
     weighing
    1.02
    WEIGHT
    0.97
     weigh
    0.97
     WEIGHT
    0.96
    weigh
    0.95
    Activations Density 0.386%

    No Known Activations