© 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. 15819
    Prev
    Next
    INDEX
    Explanations

    key lessons or principles related to emergency preparedness and safety measures

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

    formal list or outline structure, including numbered items, labeled subsections in parentheses, section headings, and enumeration-style punctuation.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    numbered lists or enumerated items in formal or technical documents.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    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
    StoryboardSegue
    -0.62
    oneofs
    -0.61
    BufferException
    -0.61
     Савезне
    -0.60
     surla
    -0.57
     picioare
    -0.56
     חיצוניים
    -0.54
     gră
    -0.54
     RIPRODUZIONE
    -0.54
    encodeWith
    -0.54
    POSITIVE LOGITS
     economy
    0.35
     economic
    0.33
    WillAppear
    0.32
     virtud
    0.31
    inderung
    0.31
     value
    0.31
     socioeconomic
    0.31
     respect
    0.30
     aspects
    0.29
     economía
    0.29
    Activations Density 0.239%

    No Known Activations