© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 5762
    Prev
    Next
    INDEX
    Explanations

    elements of graphical user interface (GUI) components and actions related to buttons and text fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -1.00
    queryInterface
    -0.66
     initComponents
    -0.61
    enumi
    -0.59
     AssemblyProduct
    -0.58
    addPreferredGap
    -0.53
    homonymie
    -0.53
    ResponseWriter
    -0.51
    جستارهای
    -0.51
    Legături
    -0.50
    POSITIVE LOGITS
    MessageOf
    0.74
    tagHelperRunner
    0.69
     brancas
    0.63
     kasarigan
    0.63
    ttino
    0.63
    NullException
    0.60
     clô
    0.60
     popoli
    0.58
     femininos
    0.58
     culturelles
    0.57
    Activations Density 0.227%

    No Known Activations