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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 9828
    Prev
    Next
    INDEX
    Explanations

    terms related to deficiencies, limitations, and poor quality in various contexts, particularly in nutrition, economics, and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.49
     (
    -0.47
    īgā
    -0.45
    NotNull
    -0.43
    chiere
    -0.43
    CDCl
    -0.43
    glMatrixMode
    -0.43
    mirante
    -0.41
     никого
    -0.41
     olmad
    -0.40
    POSITIVE LOGITS
     ―――――
    0.80
    PerformLayout
    0.77
     MenuView
    0.76
    ViewInit
    0.70
     $_"
    0.69
     Lack
    0.68
     insuffisamment
    0.68
     otomatig
    0.68
    вгений
    0.66
    (;;)
    0.66
    Activations Density 0.821%

    No Known Activations