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. 13-GEMMASCOPE-RES-16K
    6. 16235
    Prev
    Next
    INDEX
    Explanations

    terms related to health metrics and dietary references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    di
    -0.82
    getDouble
    -0.79
    //
    -0.79
    i
    -0.77
    digarh
    -0.75
    dim
    -0.74
    ble
    -0.71
     Carver
    -0.71
    imba
    -0.70
    idate
    -0.67
    POSITIVE LOGITS
     MILK
    1.14
     doubtnut
    1.00
     Milk
    0.97
     NBS
    0.96
     Pum
    0.95
     CREAM
    0.93
    Milk
    0.92
     camels
    0.91
    milk
    0.91
     Potion
    0.91
    Activations Density 0.510%

    No Known Activations