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. 20-GEMMASCOPE-RES-16K
    6. 7386
    Prev
    Next
    INDEX
    Explanations

    monetary values and price indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -0.74
    原始内容存档于
    -0.56
    ofman
    -0.56
    ')}}">
    -0.55
    NavigationView
    -0.55
    MENAFN
    -0.55
    RTRS
    -0.53
    ')}}
    -0.53
    consulté
    -0.52
     אלי
    -0.52
    POSITIVE LOGITS
     (£
    0.76
     betweenstory
    0.66
    ToAction
    0.61
     (€
    0.61
    £
    0.59
    -£
    0.59
     £
    0.57
    ituary
    0.56
    {\$
    0.56
    Rujuakan
    0.55
    Activations Density 0.121%

    No Known Activations