© 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. 4822
    Prev
    Next
    INDEX
    Explanations

    references to the mouth and related actions

    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
     jegy
    -0.55
    cheme
    -0.54
    putExtra
    -0.54
     Ki
    -0.49
    Autoritní
    -0.49
    addGap
    -0.49
    emy
    -0.48
    )_{
    -0.47
    nitzel
    -0.47
     tier
    -0.47
    POSITIVE LOGITS
     mouth
    4.29
     Mouth
    3.82
     mouths
    3.60
    mouth
    3.52
    Mouth
    3.52
    mouthed
    2.58
    MOUTH
    2.57
     bouche
    2.33
     mout
    2.30
     boca
    2.07
    Activations Density 0.058%

    No Known Activations