Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 8271
    Prev
    Next
    INDEX
    Explanations

    patterns of code structure and formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pinulongan
    -0.65
    GroupLayout
    -0.65
     typelib
    -0.64
     '\\;'
    -0.63
     ویکی‌پدی
    -0.63
    utilisons
    -0.63
    تقاوى
    -0.62
     Италијани
    -0.60
    __.__
    -0.60
     consultato
    -0.60
    POSITIVE LOGITS
     public
    0.59
    public
    0.58
    [
    0.57
    private
    0.50
    #
    0.49
    protected
    0.48
     [
    0.45
     publicly
    0.45
     pubblica
    0.43
     privata
    0.43
    Activations Density 0.023%

    No Known Activations