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. 11-GEMMASCOPE-RES-16K
    6. 6075
    Prev
    Next
    INDEX
    Explanations

    terms related to food, health, and diet

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.67
     ویکی‌پدیای
    -0.66
    GEBURTS
    -0.64
    λίου
    -0.64
    Zgod
    -0.62
     հղումներ
    -0.61
    Charsets
    -0.59
     kaarangay
    -0.58
    Obrázky
    -0.57
     GenerationType
    -0.57
    POSITIVE LOGITS
    ing
    0.73
    marshal
    0.63
    ING
    0.63
    ning
    0.59
    AsUp
    0.57
    imel
    0.55
    ">#
    0.54
    cioc
    0.54
    ting
    0.54
    bridi
    0.53
    Activations Density 0.951%

    No Known Activations