© 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. 11-GEMMASCOPE-RES-16K
    6. 12813
    Prev
    Next
    INDEX
    Explanations

    lines of code or commands related to programming and build instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PrototypeOf
    -0.65
     resourceCulture
    -0.64
    BeginContext
    -0.63
    Parcelize
    -0.60
    IRQn
    -0.59
     bezeichneter
    -0.58
     ?',
    -0.58
     muualla
    -0.57
    Datuak
    -0.56
    )]);
    -0.53
    POSITIVE LOGITS
    ="@+
    0.83
    ússia
    0.68
     ajudá
    0.68
     Garibaldi
    0.67
    #![
    0.65
    UrlResolution
    0.65
    CFLAGS
    0.61
    
    0.60
     Barnabas
    0.60
    (`/
    0.60
    Activations Density 0.091%

    No Known Activations