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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 9803
    Prev
    Next
    INDEX
    Explanations

    instances of coding commands and their attributes in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشين
    -0.75
     cref
    -0.54
     BoxFit
    -0.54
    plash
    -0.54
    PageIndex
    -0.53
    odule
    -0.51
     Kele
    -0.50
     FOL
    -0.50
    AxisAlignment
    -0.50
    runge
    -0.50
    POSITIVE LOGITS
    ValueStyle
    1.61
    RunWith
    0.93
    AddHtmlAttribute
    0.91
     eventdata
    0.84
     onCreateView
    0.80
     '{@
    0.79
     onOptions
    0.77
     تانيه
    0.76
     @"/
    0.71
    下载附件
    0.70
    Activations Density 0.016%

    No Known Activations