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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 24-GEMMASCOPE-RES-16K
    6. 8306
    Prev
    Next
    INDEX
    Explanations

    references to political figures and their actions

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

    Followed by a person's name

    np_acts-logits-general · gemini-2.0-flash

    Devin Nunes, Tom Reed, Trey Gowdy

    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
     ویکی‌پدیای
    -0.62
    ьа
    -0.60
     الحره
    -0.60
    ValueStyle
    -0.59
    rawDesc
    -0.58
    hObject
    -0.57
    ArrowToggle
    -0.56
     surla
    -0.56
    bindValue
    -0.55
    roek
    -0.53
    POSITIVE LOGITS
     Reps
    0.80
     Rep
    0.79
     Congressman
    0.78
    Reps
    0.77
     congressman
    0.77
    Rep
    0.77
     House
    0.69
     Ranking
    0.68
     Representatives
    0.67
     Representative
    0.64
    Activations Density 0.178%

    No Known Activations