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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53268
    Prev
    Next
    INDEX
    Explanations

    categories of food and drink items, including beverage and snack types

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

    food and drink items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     đ
    -0.53
     
    -0.49
    ómico
    -0.48
     record
    -0.47
    ترك
    -0.45
     what
    -0.43
    ather
    -0.43
     present
    -0.43
    erein
    -0.42
    爬
    -0.41
    POSITIVE LOGITS
     تضيفلها
    0.80
     snippetHide
    0.79
    +#+
    0.75
    曖昧さ回避
    0.75
    MigrationBuilder
    0.75
    ⓧ
    0.74
    RenderAtEndOf
    0.74
     Normdatei
    0.73
     subtypes
    0.73
    various
    0.72
    Activations Density 0.237%

    No Known Activations