© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 6648
    Prev
    Next
    INDEX
    Explanations

    elements related to form inputs and user interface elements for collecting gender information

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

    HTML form-related tokens

    np_acts-logits-general · gemini-2.0-flash

    form fields and inputs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rawDesc
    -0.67
    InSection
    -0.54
    scrapy
    -0.54
    +:+
    -0.53
    ANNES
    -0.53
     ProductService
    -0.53
    TypedDataSet
    -0.51
    vertising
    -0.49
    findpost
    -0.49
    TabStop
    -0.48
    POSITIVE LOGITS
     form
    1.11
     Form
    1.02
    form
    0.98
     forms
    0.96
    Form
    0.95
     FORM
    0.88
    forms
    0.86
     formulaire
    0.83
     Forms
    0.82
    FORM
    0.81
    Activations Density 0.280%

    No Known Activations