© 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. 11807
    Prev
    Next
    INDEX
    Explanations

    phrases related to gathering and addressing feedback from team members and external reviewers

    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
     приготування
    -0.54
    놀
    -0.53
    matchCondition
    -0.52
    AddRef
    -0.50
    GEBURTSDATUM
    -0.49
     VizieR
    -0.47
     resourceCulture
    -0.47
     quarts
    -0.47
     torchvision
    -0.47
    apimachinery
    -0.47
    POSITIVE LOGITS
     feedback
    2.43
     Feedback
    2.02
    feedback
    1.96
    Feedback
    1.86
     feedbacks
    1.67
     FEEDBACK
    1.66
     input
    1.61
     suggestions
    1.60
     comments
    1.55
    FEEDBACK
    1.49
    Activations Density 0.252%

    No Known Activations