© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 4625
    Prev
    Next
    INDEX
    Explanations

    syntax patterns and structures used in database query functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eleste
    -0.53
    AutoScaleMode
    -0.52
     रेटिंग
    -0.51
    RenderAtEndOf
    -0.51
     gynhyrchwyd
    -0.49
     trajets
    -0.49
    anoi
    -0.48
    Dauer
    -0.46
    LANTA
    -0.46
     Wikimedijinoj
    -0.46
    POSITIVE LOGITS
    colgroup
    0.63
    tangentMode
    0.63
     RIPRODUZIONE
    0.62
    webElementXpaths
    0.61
    //
    0.61
    исленность
    0.57
    camiseta
    0.57
    Autoritní
    0.56
    AxisAlignment
    0.55
     getIntent
    0.54
    Activations Density 0.294%

    No Known Activations