© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 11456
    Prev
    Next
    INDEX
    Explanations

    phrases related to errors and exceptions in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Спасылкі
    -0.59
     similar
    -0.56
    inique
    -0.55
    similar
    -0.53
    Gleich
    -0.50
     NDL
    -0.50
    Personensuche
    -0.48
    __(/*!
    -0.48
    cheinend
    -0.47
    KommentareTeilen
    -0.45
    POSITIVE LOGITS
    Otherwise
    2.28
     otherwise
    2.21
     Otherwise
    2.20
    otherwise
    2.07
     OTHERWISE
    1.85
     everything
    1.77
     ellers
    1.75
    everything
    1.73
     else
    1.65
     Everything
    1.63
    Activations Density 0.341%

    No Known Activations