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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9-GEMMASCOPE-RES-16K
    6. 7876
    Prev
    Next
    INDEX
    Explanations

    references to specific pathogens or organisms, particularly related to barley and other crops

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Gunther
    -0.93
    ongiorno
    -0.81
    GenerationType
    -0.77
     Gunt
    -0.75
     Adams
    -0.73
     Lenox
    -0.71
     jax
    -0.70
    Moh
    -0.69
    allowNull
    -0.69
    brum
    -0.68
    POSITIVE LOGITS
     Spro
    1.04
     Estelle
    0.85
     Skelton
    0.82
     PLWABN
    0.79
     LSM
    0.78
     fte
    0.74
     Ning
    0.74
    oteur
    0.73
     Caw
    0.73
     Lomb
    0.71
    Activations Density 1.623%

    No Known Activations