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. 5-GEMMASCOPE-RES-16K
    6. 12612
    Prev
    Next
    INDEX
    Explanations

    phrases related to crossing or traversing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endphp
    -0.67
    DoubleQuotes
    -0.67
    widual
    -0.64
     समीक्षाओं
    -0.62
     चीज़ों
    -0.62
    Datuak
    -0.61
    WriteTagHelper
    -0.59
    醐
    -0.59
    ValueGeneration
    -0.58
    PMailer
    -0.57
    POSITIVE LOGITS
     crossed
    1.38
     crossing
    1.32
     crosses
    1.31
     crossings
    1.25
     cross
    1.21
    crossing
    1.16
    Crossing
    1.14
    cross
    1.10
    crossed
    1.09
     Crossing
    1.08
    Activations Density 0.127%

    No Known Activations