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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5501
    Prev
    Next
    INDEX
    Explanations

    dialogue markers and emotional expressions in conversations

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

    Follows quotation marks or questions

    np_acts-logits-general · gemini-2.0-flash

    dialogue markers and responses

    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
     שוליים
    -0.56
     Chwiliwch
    -0.55
    tvguidetime
    -0.50
    DataAnnotations
    -0.47
    endous
    -0.47
    ̈́
    -0.46
    omeness
    -0.46
    IsUnicode
    -0.45
    tiérrez
    -0.45
    bootstrapcdn
    -0.45
    POSITIVE LOGITS
     replied
    0.56
    ตอบ
    0.51
     nahilalakip
    0.49
     responded
    0.44
     replies
    0.44
     answered
    0.44
     responding
    0.43
     retorted
    0.43
     responds
    0.42
     respondeu
    0.42
    Activations Density 0.098%

    No Known Activations