© 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. 2729
    Prev
    Next
    INDEX
    Explanations

    patterns or sequences of numerical values and their variations

    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
    Pre
    -0.48
    ines
    -0.48
     Pre
    -0.48
     pre
    -0.47
    pre
    -0.47
     Friday
    -0.47
    Queryable
    -0.46
     Third
    -0.43
    今
    -0.43
    isim
    -0.43
    POSITIVE LOGITS
    脚注の使い方
    0.85
    tvguidetime
    0.76
     parlé
    0.69
    RenderAtEndOf
    0.68
    expandindo
    0.66
    -------------</
    0.66
     ujednoznacz
    0.64
    ัติ
    0.64
    省市镇
    0.63
     quelcon
    0.63
    Activations Density 0.469%

    No Known Activations