© 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
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4053
    Prev
    Next
    INDEX
    Explanations

    concepts related to conflict and disputes, especially those involving families and groups

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

    words and phrases related to political conflicts, rivalries, and historical disputes.

    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
    HasAnnotation
    -0.59
     queſta
    -0.55
    DockStyle
    -0.53
    styleType
    -0.52
     ligiloj
    -0.52
    SuccessListener
    -0.52
     indígen
    -0.52
    principalColumn
    -0.51
    berdayakan
    -0.51
    cửa
    -0.50
    POSITIVE LOGITS
     conflict
    0.92
     disputes
    0.87
     dispute
    0.86
     clash
    0.82
     conflicts
    0.82
    conflict
    0.77
     clashes
    0.77
     Conflict
    0.76
     Disputes
    0.73
     controversy
    0.71
    Activations Density 0.314%

    No Known Activations