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. 7496
    Prev
    Next
    INDEX
    Explanations

    technical terms and elements related to programming and configuration settings

    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
    adaptiveStyles
    -0.56
    foglal
    -0.53
    ..."
    -0.52
    достатки
    -0.51
     sebou
    -0.51
    </strong>
    -0.50
     NSCoder
    -0.49
     '
    -0.48
    外部链接
    -0.47
    стероид
    -0.47
    POSITIVE LOGITS
    ContentAsync
    1.03
     Exacts
    0.76
    enumi
    0.76
    WriteAttribute
    0.74
    ScopeManager
    0.73
    ValueStyle
    0.72
    parsedMessage
    0.70
    帖最后由
    0.69
    ImageContext
    0.68
    MemoryWarning
    0.67
    Activations Density 0.324%

    No Known Activations