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-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 3070
    Prev
    Next
    INDEX
    Explanations

    technical terms and methods related to statistical estimation and inference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Isolated
    -0.67
     Isolated
    -0.64
    isolated
    -0.61
    Portály
    -0.55
     bezpieczeństwa
    -0.53
    KeySpec
    -0.52
    GetAxis
    -0.52
     isolated
    -0.49
    द्व
    -0.48
     Boswell
    -0.47
    POSITIVE LOGITS
     estimates
    0.80
     Estimates
    0.73
     estimators
    0.71
     estimation
    0.69
     estimate
    0.69
     fitted
    0.67
     estima
    0.67
    Estimates
    0.66
     estimator
    0.66
    RegressionTest
    0.66
    Activations Density 3.358%

    No Known Activations