Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 10670
    Prev
    Next
    INDEX
    Explanations

    terms related to healthy living and nutrition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.81
     виправивши
    -0.79
     تضيفلها
    -0.74
    èdia
    -0.72
     INTERESAR
    -0.72
     ویکی‌پدی
    -0.72
     CreateTagHelper
    -0.72
    MessageOf
    -0.71
    InSection
    -0.70
    BeginContext
    -0.70
    POSITIVE LOGITS
     alternative
    0.60
     alternatives
    0.59
    rawValue
    0.58
     growth
    0.57
     development
    0.56
    fortable
    0.54
     way
    0.54
    ikan
    0.54
     سالم
    0.53
     तरी
    0.51
    Activations Density 0.178%

    No Known Activations