Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 114911
    Prev
    Next
    INDEX
    Explanations

    connections related to media and communication technologies

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

    Common transition words or punctuation at sentence boundaries in academic or technical texts that introduce related content or examples.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Administrativna
    -0.69
    ➟
    -0.64
     Италијани
    -0.62
     &___
    -0.61
    UserScript
    -0.60
     ब्रेकडाउन
    -0.58
    principalColumn
    -0.57
    Переваги
    -0.55
    NameInMap
    -0.55
    transQ
    -0.54
    POSITIVE LOGITS
     Königin
    0.42
     dentista
    0.38
     vlasy
    0.37
     judíos
    0.37
     asiática
    0.35
     zwey
    0.35
     Freundin
    0.35
     Asien
    0.34
    signol
    0.34
     setEmail
    0.34
    Activations Density 0.187%

    No Known Activations