© 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. 22-GEMMASCOPE-RES-16K
    11. 8074
    Prev
    Next
    INDEX
    Explanations

    elements related to specific programming languages and their designed functionalities

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

    Specifically designed/intended

    np_acts-logits-general · gemini-2.0-flash

    specifically designed or intended

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.73
     الحره
    -0.70
    endphp
    -0.65
     ویکی‌پدیا
    -0.60
     onOptions
    -0.56
    󠁢
    -0.56
    čin
    -0.55
    ushchev
    -0.55
    rimônio
    -0.55
     Involved
    -0.54
    POSITIVE LOGITS
     designed
    2.41
    designed
    1.96
     intended
    1.93
     Designed
    1.85
     meant
    1.80
    Designed
    1.70
    intended
    1.68
    meant
    1.55
     dirancang
    1.52
     diseñado
    1.51
    Activations Density 0.430%

    No Known Activations