© 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. 2-GEMMASCOPE-RES-16K
    11. 4801
    Prev
    Next
    INDEX
    Explanations

    the word "anyway."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ://"
    -0.66
     sekä
    -0.53
     past
    -0.53
     newly
    -0.50
     +
    -0.50
    "));
    -0.49
    cmath
    -0.49
    ждую
    -0.48
     ✓
    -0.48
     bislang
    -0.48
    POSITIVE LOGITS
     anyway
    3.56
    anyway
    3.28
     Anyway
    3.26
    Anyway
    3.14
     anyways
    3.01
     Anyways
    2.63
     anyhow
    2.62
    Anyways
    2.60
    Anyhow
    2.09
     comunque
    1.45
    Activations Density 0.091%

    No Known Activations