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

    Neuronpedia

    APICircuit 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. 25-GEMMASCOPE-RES-16K
    6. 10227
    Prev
    Next
    INDEX
    Explanations

    elements related to health and nutrition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.57
    曖昧さ回避
    -0.57
    (&$
    -0.52
     Wikimédia
    -0.52
    msgTypes
    -0.47
     Waterfront
    -0.47
     pecuni
    -0.46
     schwarze
    -0.44
     Enterprise
    -0.44
     Wet
    -0.44
    POSITIVE LOGITS
     cells
    0.80
     metabo
    0.79
     Cells
    0.74
     organs
    0.74
     CELLS
    0.71
    Cells
    0.69
     hormones
    0.69
     metabolism
    0.69
     tissues
    0.67
    TagMode
    0.65
    Activations Density 0.314%

    No Known Activations