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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 7891
    Prev
    Next
    INDEX
    Explanations

    specific structural elements, specifically related to coding or programming constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preceding tokens of "form"

    np_acts-logits-general · gemini-2.0-flash

    in the form

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interopRequire
    -0.77
    adaptiveStyles
    -0.73
     ویکی‌پدیا
    -0.71
    SpringRunner
    -0.71
     متعلقه
    -0.69
    InSection
    -0.66
    esModule
    -0.63
    下载附件
    -0.61
    EDEFAULT
    -0.59
    JNIEnv
    -0.57
    POSITIVE LOGITS
     form
    4.27
    form
    3.79
     Form
    3.74
    Form
    3.62
     FORM
    3.35
     forms
    3.30
     Forms
    2.99
    FORM
    2.95
     forma
    2.84
    forms
    2.78
    Activations Density 0.475%

    No Known Activations