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. 15-GEMMASCOPE-RES-16K
    6. 5099
    Prev
    Next
    INDEX
    Explanations

    XML tags related to group or artifact identifiers in Maven dependencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bParam
    -0.62
    RUnlock
    -0.60
    ंदीखरीदारी
    -0.57
     pstmt
    -0.56
    Citiți
    -0.55
    tım
    -0.54
    peño
    -0.53
     المعيارى
    -0.53
    rrggbb
    -0.51
    ✭✭
    -0.50
    POSITIVE LOGITS
     {@
    1.20
    {@
    1.14
    verwijspagina
    0.71
    TagMode
    0.71
     AssemblyProduct
    0.70
    原始内容存档于
    0.69
    bkz
    0.66
    Viited
    0.60
    HasBeenSet
    0.59
     ***!
    0.56
    Activations Density 0.004%

    No Known Activations