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. 3-GEMMASCOPE-RES-16K
    6. 7362
    Prev
    Next
    INDEX
    Explanations

    specific formatting or structure elements commonly used in coding or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndGlobalSection
    -0.87
    UserScript
    -0.71
    /*
    -0.70
    ArgsConstructor
    -0.68
     Infórmanos
    -0.67
    Tikang
    -0.66
     MenuView
    -0.65
    Хьажоргаш
    -0.65
    DotNetBar
    -0.64
    estries
    -0.64
    POSITIVE LOGITS
    taj
    0.46
     elettron
    0.42
     mecán
    0.42
     المعيارى
    0.42
    )++;
    0.41
    Hozzáférés
    0.40
     laiton
    0.40
    bic
    0.38
     Scale
    0.38
     élas
    0.38
    Activations Density 0.386%

    No Known Activations