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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 75049
    Prev
    Next
    INDEX
    Explanations

    terms related to user privacy and data handling

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

    legal and technical jargon

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     democrática
    -0.49
     legales
    -0.48
     métiers
    -0.44
     Drummond
    -0.44
     boneka
    -0.42
     judiciales
    -0.41
     inalámbrica
    -0.40
     animación
    -0.39
     Schnell
    -0.39
     democracia
    -0.39
    POSITIVE LOGITS
     Italijanski
    0.85
    parsedMessage
    0.76
     Савезне
    0.74
    хьтан
    0.73
    SharedDtor
    0.70
    цездатний
    0.69
     nahilalakip
    0.67
     ویکی‌پدی
    0.67
     unknownFields
    0.65
    Jeografia
    0.64
    Activations Density 0.014%

    No Known Activations