© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 5089
    Prev
    Next
    INDEX
    Explanations

    notifications and announcements related to events or changes in services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.62
    LabelTagHelper
    -0.44
    nestjs
    -0.43
    elsch
    -0.42
    ValueStyle
    -0.42
    期刊论文
    -0.41
    AnchorStyles
    -0.40
    انيف
    -0.40
     오
    -0.40
    Portale
    -0.40
    POSITIVE LOGITS
    ρεύ
    0.69
     ExecuteAsync
    0.66
     Paglinawan
    0.63
    soort
    0.59
    πως
    0.57
    amation
    0.56
    bufio
    0.56
    onsored
    0.55
    polazione
    0.55
    <bos>
    0.55
    Activations Density 0.835%

    No Known Activations