© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4220
    Prev
    Next
    INDEX
    Explanations

    reported speech and quotes in the text

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

    Attribution of quotes

    np_acts-logits-general · gemini-2.0-flash

    verbs of speech, thought, and finding

    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
    EndContext
    -0.40
    ท์
    -0.39
     Cos
    -0.39
    
    -0.38
     cos
    -0.38
     forsaken
    -0.37
     Pry
    -0.37
    ding
    -0.37
     μό
    -0.37
    WebElementEntity
    -0.36
    POSITIVE LOGITS
    出版年
    0.56
    MessageOf
    0.52
     CreateTagHelper
    0.50
     informée
    0.50
    참고
    0.44
    ніципалі
    0.41
     frågan
    0.41
    crites
    0.40
     aload
    0.39
     ChromeDriver
    0.39
    Activations Density 0.162%

    No Known Activations