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. 10-GEMMASCOPE-RES-16K
    6. 2129
    Prev
    Next
    INDEX
    Explanations

    keywords related to access modifiers and visibility in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ostante
    -0.88
    +:+
    -0.86
    LayoutStyle
    -0.85
     ujednoznacz
    -0.85
    lccn
    -0.84
    
    -0.84
     onOptions
    -0.83
    تقاوى
    -0.83
     poppies
    -0.80
     officiellement
    -0.78
    POSITIVE LOGITS
    private
    1.17
     Private
    0.97
     private
    0.97
     Privat
    0.85
    PRIVATE
    0.83
    Private
    0.82
     privat
    0.78
     PRIVATE
    0.77
    Privat
    0.75
    ::::::::::::::::
    0.74
    Activations Density 0.027%

    No Known Activations