© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10672
    Prev
    Next
    INDEX
    Explanations

    references to family relationships and offspring

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

    children, sons, or daughters

    np_acts-logits-general · gemini-2.0-flash

    children, sons, and daughters

    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
    下载附件
    -0.47
    utilisons
    -0.40
    postsleuth
    -0.40
     implication
    -0.38
    prits
    -0.37
    wein
    -0.36
    richTextPanel
    -0.36
    Repeti
    -0.36
    Neces
    -0.36
    inderung
    -0.35
    POSITIVE LOGITS
     sons
    0.54
     daughters
    0.51
     filhos
    0.48
     Daughter
    0.47
     Sons
    0.47
     Daughters
    0.46
    MLLoader
    0.46
    usermodel
    0.45
    Sons
    0.44
     grandchildren
    0.43
    Activations Density 0.035%

    No Known Activations