© 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. 5-GEMMASCOPE-RES-16K
    11. 2930
    Prev
    Next
    INDEX
    Explanations

    variations of the word "commit" in various contexts related to criminal acts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases related to committing or intent to commit various actions, particularly illegal ones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Havolalar
    -0.78
    сылкі
    -0.72
    daß
    -0.66
    Източници
    -0.66
    awtextra
    -0.65
    OrBuilder
    -0.64
    IsMutable
    -0.64
     daß
    -0.63
    Tracce
    -0.63
    CURLOPT
    -0.63
    POSITIVE LOGITS
     commit
    1.69
    commit
    1.68
     Commit
    1.67
     committing
    1.58
    Commit
    1.57
     commits
    1.50
     COMMIT
    1.32
    COMMIT
    1.22
     committed
    1.22
    commits
    1.17
    Activations Density 0.074%

    No Known Activations