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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 24-GEMMASCOPE-RES-131K
    6. 1224
    Prev
    Next
    INDEX
    Explanations

    references to the name "Jack" or play on words involving "jack."

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

    Jack, Jacks, jack-up, Jacky

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.55
     Crespo
    -0.49
    AnimationsModule
    -0.48
     Molina
    -0.46
     Morin
    -0.46
    omo
    -0.44
    th
    -0.44
     Cronin
    -0.43
     Fiore
    -0.43
    hlen
    -0.43
    POSITIVE LOGITS
     Jack
    0.95
    Jack
    0.94
     JACK
    0.88
    JACK
    0.87
     Jacks
    0.84
     Monfieur
    0.83
     rodríguez
    0.83
     Jackman
    0.81
     sánchez
    0.79
    jsonwebtoken
    0.75
    Activations Density 0.004%

    No Known Activations