© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 600
    Prev
    Next
    INDEX
    Explanations

    conversational interactions and farewells

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

    French conversation and chat-like interactions, especially those involving saying goodbye or expressing gratitude.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    ISIONS
    -0.46
    cyd
    -0.39
    一来
    -0.39
    giarism
    -0.37
     colorWith
    -0.37
    neid
    -0.37
    Ƚ
    -0.36
    abaikan
    -0.36
    bitt
    -0.34
    的呢
    -0.34
    POSITIVE LOGITS
     disambiguazione
    0.71
    webElementXpaths
    0.56
    StructEnd
    0.53
    MessageTagHelper
    0.53
     allAfrica
    0.52
    IUrlHelper
    0.49
    Portale
    0.48
    writeFieldEnd
    0.47
    قایناق‌لار
    0.46
    IndentedString
    0.46
    Activations Density 0.266%

    No Known Activations