© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 35468
    Prev
    Next
    INDEX
    Explanations

    the name "Peters" and references to individuals associated with it

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

    Peters, Franks, Patty, tomogram

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bentley
    -0.59
    Zü
    -0.56
     Cagliari
    -0.55
    Bentley
    -0.54
    Switzerland
    -0.54
     pleaſure
    -0.54
    Norwegian
    -0.54
    Norway
    -0.54
    Stuttgart
    -0.54
     Huxley
    -0.53
    POSITIVE LOGITS
     Peters
    2.23
    Peters
    2.03
     PETERS
    1.82
     pet
    0.66
     Petersen
    0.66
     Petersburg
    0.66
     pets
    0.63
     Pet
    0.63
    pet
    0.61
    Pet
    0.57
    Activations Density 0.003%

    No Known Activations