© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4422
    Prev
    Next
    INDEX
    Explanations

    fields and labels related to contact information and data submission forms

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

    form or contact-related fields and keywords, such as email, name, phone, and message sections in web forms or contact pages.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wijk
    -0.39
    MigrationBuilder
    -0.38
     Einstellung
    -0.38
    ksikon
    -0.38
     hoogte
    -0.38
     Auflösung
    -0.36
     Magellan
    -0.36
     Spannung
    -0.35
     magnética
    -0.35
     SQUARE
    -0.34
    POSITIVE LOGITS
    contentLoaded
    0.57
     submit
    0.55
    PMailer
    0.54
     email
    0.52
    DispatchToProps
    0.52
    AISSEE
    0.51
    Civ
    0.51
    Submit
    0.50
     emailing
    0.50
    sproz
    0.49
    Activations Density 0.097%

    No Known Activations