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-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 10247
    Prev
    Next
    INDEX
    Explanations

    repeated mentions of the name "Jo."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.74
    ViewFeatures
    -0.68
    kloped
    -0.63
     conden
    -0.58
     Zephyr
    -0.57
     Nebel
    -0.57
    xiii
    -0.57
    Demografie
    -0.56
    Msp
    -0.56
    +#+
    -0.55
    POSITIVE LOGITS
     Jo
    3.07
     jo
    2.88
    Jo
    2.88
    jo
    2.48
    JO
    2.26
     JO
    2.19
     Joi
    1.50
     Joanne
    1.41
     Jock
    1.33
     JOIN
    1.32
    Activations Density 0.087%

    No Known Activations