© 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. 21-GEMMASCOPE-RES-16K
    11. 15009
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases associated with political and security issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    原始内容存档于
    -0.85
    esModule
    -0.77
    protoimpl
    -0.76
    KommentareTeilen
    -0.75
     cherchés
    -0.72
     Signalez
    -0.72
    ParallelGroup
    -0.70
    تقاوى
    -0.68
    findpost
    -0.67
     שוליים
    -0.67
    POSITIVE LOGITS
     White
    0.80
    White
    0.64
     Treasury
    0.64
     Secretary
    0.63
     OMB
    0.59
    Treasury
    0.58
    OMB
    0.56
     Obama
    0.54
     HHS
    0.53
     администра
    0.50
    Activations Density 0.413%

    No Known Activations