Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 4546
    Prev
    Next
    INDEX
    Explanations

    code-related elements or structures in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AliExpress
    -0.53
    ThroughAttribute
    -0.51
     Cot
    -0.50
    Gambas
    -0.49
     your
    -0.49
     NgModule
    -0.48
     Nop
    -0.47
    awtextra
    -0.47
    resave
    -0.46
     enda
    -0.46
    POSITIVE LOGITS
     مرئيه
    0.83
    Minnesota
    0.67
    nesota
    0.67
    ազմ
    0.66
    存于互联网档案馆
    0.65
     SVG
    0.63
    selectAll
    0.63
     Duluth
    0.61
     Minnesota
    0.60
     Вікі
    0.58
    Activations Density 0.046%

    No Known Activations