Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 7714
    Prev
    Next
    INDEX
    Explanations

    dialogue and speech-related expressions between characters

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

    Follows a person's name or pronoun, and a speech verb

    np_acts-logits-general · gemini-2.0-flash

    pronoun says

    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
    principalTable
    -0.54
     förstå
    -0.54
    rowad
    -0.52
     bakso
    -0.48
     insegna
    -0.48
     postale
    -0.47
     connaissent
    -0.47
     bev
    -0.47
     caccia
    -0.47
     VizieR
    -0.46
    POSITIVE LOGITS
     whispered
    1.06
     muttered
    0.96
     mumbled
    0.94
     murmured
    0.91
     shouted
    0.85
     whispers
    0.85
    脚注の使い方
    0.84
     exclaimed
    0.83
     whisper
    0.82
     yelled
    0.77
    Activations Density 0.033%

    No Known Activations