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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 10540
    Prev
    Next
    INDEX
    Explanations

    specific technical or analytical terms related to various specialized fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ErrIntOverflow
    -0.75
     OFDb
    -0.65
     Monfieur
    -0.65
     juſ
    -0.65
     juſt
    -0.64
     Majefty
    -0.63
     uſed
    -0.62
    GEBURTSDATUM
    -0.62
     initComponents
    -0.62
    XtraReports
    -0.60
    POSITIVE LOGITS
    Tembelea
    0.73
    numerusform
    0.52
    __);
    0.51
     ddelweddau
    0.47
     raya
    0.46
     дописавши
    0.45
     gesteld
    0.44
    '>";
    0.43
    $.}
    0.42
     NgModule
    0.41
    Activations Density 2.243%

    No Known Activations