© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14287
    Prev
    Next
    INDEX
    Explanations

    temporal references and significant events

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

    time or dates

    np_acts-logits-general · gemini-2.0-flash

    recent past time periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    engelsk
    -0.39
    </tfoot>
    -0.31
    녁
    -0.29
     scon
    -0.29
     Coming
    -0.29
    testens
    -0.28
    sätzlich
    -0.28
    Hochspringen
    -0.28
     TIR
    -0.26
     circun
    -0.26
    POSITIVE LOGITS
     recently
    0.74
    recently
    0.70
    hoeddwyd
    0.68
    Recently
    0.67
     recientemente
    0.66
     recentemente
    0.66
     Recently
    0.65
     InputDecoration
    0.61
     недавно
    0.58
     recent
    0.57
    Activations Density 0.229%

    No Known Activations