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. 7885
    Prev
    Next
    INDEX
    Explanations

    terms related to pathogenic mechanisms and genetic factors involved in diseases

    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
    tvguidetime
    -0.82
     AssemblyCulture
    -0.77
    +#+#
    -0.75
    ViewFeatures
    -0.69
     ujednoznacz
    -0.61
    avyzd
    -0.57
     inconn
    -0.56
     Macromolecules
    -0.55
    PerformLayout
    -0.55
     quelquefois
    -0.55
    POSITIVE LOGITS
    '),
    
    0.65
    )’
    0.65
    리는
    0.62
     will
    0.60
    Décès
    0.60
    ]`
    0.60
    )'
    0.59
    들은
    0.58
    )
    
    
    0.58
    ният
    0.57
    Activations Density 2.807%

    No Known Activations