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. 20-GEMMASCOPE-RES-16K
    6. 16157
    Prev
    Next
    INDEX
    Explanations

    code related to functions and methods, particularly in the context of programming frameworks

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

    Code snippets or programming-related content

    np_acts-logits-general · gemini-2.0-flash

    `the new`, `the Mage`, `the ore`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     idéia
    -0.80
    berdayakan
    -0.58
     daß
    -0.56
     XHTML
    -0.56
    WebControls
    -0.52
     éstas
    -0.52
    polate
    -0.51
    OutputType
    -0.49
     éstos
    -0.48
     démission
    -0.48
    POSITIVE LOGITS
     Covid
    0.68
     nullptr
    0.67
     COVID
    0.67
     $"{
    0.66
    ([...
    0.64
     covid
    0.64
     nameof
    0.63
     ElevatedButton
    0.61
    [...,
    0.60
     [...
    0.58
    Activations Density 0.094%

    No Known Activations