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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 5598
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and structures, particularly those involving square roots and integers

    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
    SceneManagement
    -0.74
    +#+
    -0.64
    EndContext
    -0.58
    
    -0.55
     nemlig
    -0.52
    +#+#
    -0.51
     ExecuteAsync
    -0.51
    btnLogin
    -0.49
     Numerade
    -0.48
     totiž
    -0.47
    POSITIVE LOGITS
     تضيفلها
    0.68
     viewType
    0.63
    NameInMap
    0.59
    ally
    0.58
    halb
    0.58
    domo
    0.56
    tium
    0.56
    uez
    0.56
    ISupport
    0.56
    dial
    0.56
    Activations Density 0.555%

    No Known Activations