© 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. 3560
    Prev
    Next
    INDEX
    Explanations

    Java access modifiers and static keywords in code

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

    "final"

    np_acts-logits-general · gemini-2.0-flash

    final

    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
    Билгалдахарш
    -0.49
    зя
    -0.47
     saja
    -0.46
    issimo
    -0.45
    ContentAsync
    -0.44
    írus
    -0.43
    гипет
    -0.43
     podjela
    -0.43
     Gegenteil
    -0.42
     cuotas
    -0.42
    POSITIVE LOGITS
     final
    3.76
    final
    3.58
    Final
    2.67
     FINAL
    2.67
     Final
    2.61
    FINAL
    2.49
     finally
    2.29
    最终
    2.06
     Finally
    1.96
    最終
    1.94
    Activations Density 0.134%

    No Known Activations