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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 14044
    Prev
    Next
    INDEX
    Explanations

    keywords related to calling functions and invoking methods in programming

    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
    KommentareTeilen
    -0.59
     الحره
    -0.56
     acrylique
    -0.55
    RegressionTest
    -0.55
     initComponents
    -0.54
    úrese
    -0.54
    featureID
    -0.53
    ██
    -0.51
    Possui
    -0.51
    djangoproject
    -0.50
    POSITIVE LOGITS
     call
    2.49
     Call
    2.42
    Call
    2.37
     CALL
    2.36
     calls
    2.31
    CALL
    2.26
    call
    2.24
     Calls
    2.19
     calling
    2.17
    calls
    2.08
    Activations Density 0.120%

    No Known Activations