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. 15130
    Prev
    Next
    INDEX
    Explanations

    terms related to membrane proteins and their functions in cellular processes

    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
     Montal
    -0.86
    {`
    -0.85
     Spal
    -0.83
    Okey
    -0.80
    }>\
    -0.78
    flik
    -0.78
     panto
    -0.77
    heen
    -0.76
    Amal
    -0.76
    orean
    -0.76
    POSITIVE LOGITS
    AndEndTag
    0.88
     Uribe
    0.87
     Mathews
    0.86
     YU
    0.86
    lamps
    0.85
     العاده
    0.83
    ArrowToggle
    0.83
    ิลปะ
    0.82
     Dinah
    0.82
    jména
    0.81
    Activations Density 2.325%

    No Known Activations