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. 16-GEMMASCOPE-RES-16K
    6. 1687
    Prev
    Next
    INDEX
    Explanations

    references to scientific journals and articles, especially those that include volume and page numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Citations with volume and page numbers

    np_acts-logits-general · gemini-2.0-flash

    scientific and technical articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Einfluß
    -0.56
    --
    -0.55
     daß
    -0.55
     muß
    -0.53
    न्द्र
    -0.52
     références
    -0.51
     onlyOwner
    -0.50
     angeles
    -0.50
    TRIBUN
    -0.49
    #+#
    -0.49
    POSITIVE LOGITS
     doInBackground
    0.68
     TikTok
    0.68
     constexpr
    0.68
    Personensuche
    0.67
    StandardCharsets
    0.66
     COVID
    0.66
     $"{
    0.65
    COVID
    0.65
    . 
    0.64
    RegistryLite
    0.64
    Activations Density 0.959%

    No Known Activations