© 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 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. 1484
    Prev
    Next
    INDEX
    Explanations

    instances of the word "raise" and its variations, often in the context of exceptions or errors

    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
     Woodruff
    -0.57
    KommentareTeilen
    -0.57
    +#+#
    -0.53
    myn
    -0.52
    mml
    -0.52
    WithString
    -0.50
    THRESH
    -0.49
    userdetails
    -0.48
    INSEE
    -0.48
     catholique
    -0.47
    POSITIVE LOGITS
    raise
    2.84
    Raise
    1.72
     Raise
    1.66
     raise
    1.65
    raises
    1.46
     raises
    1.34
    Raises
    1.21
     raising
    1.18
     Raises
    1.13
     Raising
    1.10
    Activations Density 0.050%

    No Known Activations