© 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. 14177
    Prev
    Next
    INDEX
    Explanations

    events related to celebrations or formal gatherings

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

    Events and gatherings

    np_acts-logits-general · gemini-2.0-flash

    event outcomes and conclusions

    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
     atualmente
    -0.43
     actuellement
    -0.42
     prêtres
    -0.41
    retudo
    -0.41
     actualmente
    -0.41
     prochaines
    -0.39
     plufieurs
    -0.38
     primario
    -0.38
     edelstahl
    -0.37
    RTSN
    -0.37
    POSITIVE LOGITS
     danced
    0.63
     was
    0.62
     cheered
    0.60
     drew
    0.59
     took
    0.59
    AndEndTag
    0.58
     glowed
    0.57
     did
    0.57
    took
    0.55
     attendees
    0.55
    Activations Density 0.184%

    No Known Activations