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. 2926
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structure related to user interface layout and design

    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
     chất
    -0.52
     vej
    -0.50
    isand
    -0.48
     кем
    -0.48
     reflecting
    -0.48
    StructEnd
    -0.47
    innerHTML
    -0.46
     chod
    -0.46
    pensive
    -0.46
     reflects
    -0.45
    POSITIVE LOGITS
    esgue
    1.02
    awtextra
    0.96
     CGRectMake
    0.86
    AnchorStyles
    0.84
    CGRectMake
    0.82
     BoxDecoration
    0.82
    RectangleBorder
    0.80
    makeConstraints
    0.79
     snippetHide
    0.78
    ConstraintMaker
    0.75
    Activations Density 0.011%

    No Known Activations