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. 1-GEMMASCOPE-RES-16K
    6. 13127
    Prev
    Next
    INDEX
    Explanations

    the presence of various input types in form elements, particularly in HTML or script context

    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
    tagHelperRunner
    -0.71
    TagHelpers
    -0.69
    localctx
    -0.69
     CORS
    -0.67
     ujednoznacz
    -0.64
    참고
    -0.64
    ConstraintMaker
    -0.62
    AxisSize
    -0.61
    CloseOperation
    -0.61
    AxisAlignment
    -0.61
    POSITIVE LOGITS
    MathML
    0.84
     type
    0.77
     humo
    0.63
    はじめに
    0.59
     estr
    0.53
    Spacing
    0.52
    teles
    0.52
    ixon
    0.52
    wanan
    0.51
    hofen
    0.51
    Activations Density 0.192%

    No Known Activations