© 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. 20-GEMMASCOPE-RES-16K
    11. 5439
    Prev
    Next
    INDEX
    Explanations

    numerical data or values

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

    figures or tables

    np_acts-logits-general · gemini-2.0-flash

    figure references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FOO
    -0.52
     Platform
    -0.51
     platform
    -0.51
     Osorio
    -0.50
     commerciali
    -0.50
    Filmo
    -0.49
     negativo
    -0.48
    DEO
    -0.47
    platform
    -0.47
    framed
    -0.47
    POSITIVE LOGITS
    TintMode
    0.85
    ьаж
    0.77
    MemoryWarning
    0.77
    InjectAttribute
    0.75
    StoryboardSegue
    0.74
    دانشنامهٔ
    0.73
    NameInMap
    0.72
    RegressionTest
    0.72
     صوتيه
    0.69
    ArrowToggle
    0.69
    Activations Density 0.403%

    No Known Activations