© 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. 1-GEMMASCOPE-RES-16K
    11. 14721
    Prev
    Next
    INDEX
    Explanations

    elements related to rows and columns in a table structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ReSharper
    -0.65
     raiſ
    -0.62
     Reſ
    -0.62
     doubtnut
    -0.61
     pleaſure
    -0.58
     poffible
    -0.58
    IVERY
    -0.56
    SSON
    -0.56
    ectady
    -0.56
    }{*}{
    -0.56
    POSITIVE LOGITS
    таратура
    0.71
     kasarigan
    0.69
    row
    0.67
    SESSION
    0.66
    scope
    0.65
    EnableWeb
    0.64
     NgModule
    0.64
     AssemblyCulture
    0.63
    المناصب
    0.62
     مشين
    0.62
    Activations Density 0.072%

    No Known Activations