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. 3-GEMMASCOPE-RES-16K
    6. 8351
    Prev
    Next
    INDEX
    Explanations

    terms related to cooking methods and types of food preparation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Karya
    -0.54
    FirstResponder
    -0.52
     cucchiaio
    -0.52
     courbe
    -0.51
    oquia
    -0.51
     olhos
    -0.51
     enero
    -0.51
    avía
    -0.51
     CET
    -0.50
     nyata
    -0.50
    POSITIVE LOGITS
     grill
    2.74
     Grill
    2.51
     grills
    2.40
    Grill
    2.25
    grill
    2.25
     grilled
    2.24
     grilling
    2.12
     Grilled
    2.06
    grilled
    2.05
    Grilled
    1.84
    Activations Density 0.108%

    No Known Activations