© 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. 7698
    Prev
    Next
    INDEX
    Explanations

    references to the term "punch" in various contexts

    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
    Autoritní
    -0.88
    +#+#
    -0.88
     Мексичка
    -0.87
    évaluateur
    -0.87
     pinulongan
    -0.83
    lapsingToolbar
    -0.82
    PerformLayout
    -0.80
     skimage
    -0.79
     GenerationType
    -0.75
    actionMode
    -0.75
    POSITIVE LOGITS
     punch
    1.31
     punches
    1.25
    pun
    1.24
     Pun
    1.24
    punch
    1.23
     Punch
    1.19
    Pun
    1.18
    Punch
    1.13
     punched
    1.09
     pun
    1.02
    Activations Density 0.238%

    No Known Activations