© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6983
    Prev
    Next
    INDEX
    Explanations

    historical dates and time references

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

    Numerical day/time indicators

    np_acts-logits-general · gemini-2.0-flash

    when temporal events

    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
    قایناقلار
    -0.60
    parsedMessage
    -0.59
     jScrollPane
    -0.54
    ThroughAttribute
    -0.51
    ("}");
    -0.48
    月号
    -0.48
    ьаж
    -0.47
    RoutingModule
    -0.46
     useAuth
    -0.46
    ArrowToggle
    -0.45
    POSITIVE LOGITS
     when
    3.74
    when
    3.12
     quando
    2.82
     cuando
    2.82
     WHEN
    2.56
    When
    2.52
     когда
    2.51
     When
    2.48
     lorsque
    2.36
    WHEN
    2.32
    Activations Density 1.587%

    No Known Activations