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

    Neuronpedia

    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. 2-GEMMASCOPE-RES-16K
    11. 5588
    Prev
    Next
    INDEX
    Explanations

    functions or callbacks in a programming context, especially those handling conditional logic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -0.55
    RequestMapping
    -0.53
     Bowman
    -0.53
     تضيفلها
    -0.52
    __*/
    -0.51
     fieldNum
    -0.50
     Signalez
    -0.50
     enca
    -0.50
    スタム
    -0.49
     Pref
    -0.49
    POSITIVE LOGITS
    ={()
    0.86
     تانيه
    0.81
     Efq
    0.81
    ={()=>
    0.81
     nargin
    0.78
     kinds
    0.77
    LLocation
    0.77
     Anſ
    0.77
     Notion
    0.74
     Jefus
    0.74
    Activations Density 0.022%

    No Known Activations