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. 10-GEMMASCOPE-RES-16K
    6. 3017
    Prev
    Next
    INDEX
    Explanations

    terms related to mitochondrial metabolism and energy production

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bege
    -0.57
    ட்ச
    -0.51
    ština
    -0.48
     चु
    -0.47
     Bea
    -0.46
     developed
    -0.46
    imshow
    -0.46
     
    -0.45
    iz
    -0.44
     Phil
    -0.44
    POSITIVE LOGITS
    TypedDataSet
    1.00
    IsMutable
    0.99
    WebVitals
    0.97
     /\.(
    0.89
    Portale
    0.89
    expandindo
    0.88
    ftagPool
    0.86
     onCancelled
    0.85
    ंदीखरीदारी
    0.84
    TagMode
    0.83
    Activations Density 1.224%

    No Known Activations