© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 6839
    Prev
    Next
    INDEX
    Explanations

    sections of text marked for data structure headers or types of formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ghijkl
    -0.53
    Enllaços
    -0.52
    criture
    -0.49
    findOrFail
    -0.49
     soudain
    -0.49
    lardır
    -0.48
     
    -0.48
    expandindo
    -0.47
     portata
    -0.46
    Kli
    -0.46
    POSITIVE LOGITS
    Composable
    0.59
     ostavi
    0.58
    printStackTrace
    0.55
     INTERESAR
    0.53
     Affiliations
    0.52
    DispatchToProps
    0.50
     CanadaChoose
    0.50
    θο
    0.50
    RegressionTest
    0.50
     CURIAM
    0.49
    Activations Density 0.089%

    No Known Activations