Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 2688
    Prev
    Next
    INDEX
    Explanations

    references to ratings and reviews, particularly in a customer feedback context

    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
    setVerticalGroup
    -1.01
    DockStyle
    -0.91
    \{\\
    -0.85
    UrlResolution
    -0.83
     CreateTagHelper
    -0.81
    ]--;
    -0.80
    Willkommen
    -0.74
     Baillargeon
    -0.73
     AspNetCore
    -0.72
    EndGlobalSection
    -0.71
    POSITIVE LOGITS
     review
    0.61
     nice
    0.60
     Review
    0.58
    nice
    0.57
     excellent
    0.57
    Review
    0.56
     Reviewed
    0.56
     Excellent
    0.55
    review
    0.54
     reviewed
    0.54
    Activations Density 0.079%

    No Known Activations