© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 15706
    Prev
    Next
    INDEX
    Explanations

    food-related terms and dishes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Deep fried food or snacks

    np_acts-logits-general · gemini-2.0-flash

    deep fried food

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ьаж
    -0.65
     CreateTagHelper
    -0.62
     дописавши
    -0.61
     consuls
    -0.52
     Bourgoin
    -0.51
    >`;
    -0.51
    mpä
    -0.50
    ituary
    -0.49
     databases
    -0.48
    ガニック
    -0.48
    POSITIVE LOGITS
     snack
    0.76
     snacks
    0.74
     deep
    0.70
     frit
    0.67
     bites
    0.66
     bite
    0.65
     Deep
    0.65
     Snacks
    0.65
    Deep
    0.64
     puffs
    0.64
    Activations Density 0.146%

    No Known Activations