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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 6204
    Prev
    Next
    INDEX
    Explanations

    elements related to HTML forms and their structure

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

    the word "form" (or "forms")

    np_acts-logits-general · gemini-2.0-flash

    form and forms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    printStackTrace
    -0.63
    GoogleApiClient
    -0.59
     McAllister
    -0.57
     myel
    -0.56
    pecially
    -0.54
    getStringExtra
    -0.53
     Kabel
    -0.53
    pixel
    -0.53
    逸
    -0.52
    penny
    -0.51
    POSITIVE LOGITS
     Form
    1.13
     form
    1.08
     FORM
    1.02
    form
    1.02
    Form
    1.01
     Forms
    0.87
     forms
    0.82
    FORM
    0.82
    getForm
    0.79
    Forms
    0.78
    Activations Density 0.158%

    No Known Activations