© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 8761
    Prev
    Next
    INDEX
    Explanations

    form elements in HTML code related to gender selection

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

    HTML radio buttons or checkboxes

    np_acts-logits-general · gemini-2.0-flash

    checkbox input state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
     CreateTagHelper
    -0.64
     AspNetCore
    -0.60
    StructEnd
    -0.56
    leit
    -0.52
     esper
    -0.51
    دانشنامهٔ
    -0.50
    lanta
    -0.50
     entityManager
    -0.50
    پیوند
    -0.50
    ObjectContext
    -0.49
    POSITIVE LOGITS
     checked
    1.76
     checkbox
    1.54
     check
    1.54
    checked
    1.53
     Checked
    1.47
     CHECK
    1.45
    Checked
    1.43
    check
    1.39
     Check
    1.35
    checkbox
    1.35
    Activations Density 0.170%

    No Known Activations