© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 2860
    Prev
    Next
    INDEX
    Explanations

    events related to conferences and workshops

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

    Conference, meeting, or event

    np_acts-logits-general · gemini-2.0-flash

    conference and events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.39
     explicación
    -0.39
     cappuccio
    -0.35
     vecind
    -0.34
    ReusableCell
    -0.33
     wachten
    -0.33
    appartamento
    -0.32
     daglig
    -0.32
     borboleta
    -0.32
    disposing
    -0.32
    POSITIVE LOGITS
     conference
    0.87
     convention
    0.84
     conferences
    0.80
    Conference
    0.78
     Conference
    0.77
    conference
    0.77
     konfer
    0.74
    で開催
    0.74
    convention
    0.73
     workshop
    0.72
    Activations Density 0.226%

    No Known Activations