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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 2879
    Prev
    Next
    INDEX
    Explanations

    tokens related to programming syntax and structures, particularly involving function definitions and conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.58
    antaranya
    -0.57
    argout
    -0.56
    Captor
    -0.53
    LayoutConstraint
    -0.53
     ویکی‌پدیا
    -0.52
    openzeppelin
    -0.51
    AddHtmlAttribute
    -0.50
     стъ
    -0.49
    RTLR
    -0.49
    POSITIVE LOGITS
    migrationBuilder
    0.67
    tagHelperRunner
    0.61
     Bioaccumulative
    0.60
    +#+#
    0.57
     True
    0.56
    EndProject
    0.55
     Bourgoin
    0.55
    true
    0.54
     ivelany
    0.53
     للمعارف
    0.52
    Activations Density 0.421%

    No Known Activations