© 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. 10-GEMMASCOPE-RES-16K
    6. 4359
    Prev
    Next
    INDEX
    Explanations

    activities related to ongoing projects and clinical trials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EventHandler
    -0.49
    byr
    -0.49
     Meksiku
    -0.46
     QtCore
    -0.45
     anteriormente
    -0.44
     ttk
    -0.44
    cedent
    -0.43
     EdgeInsets
    -0.43
    IBarButtonItem
    -0.43
    pmd
    -0.42
    POSITIVE LOGITS
    ValueStyle
    1.00
    RenderAtEndOf
    0.69
    EndProject
    0.69
    FieldBuilder
    0.68
     gespannt
    0.68
     Currently
    0.67
     undergoing
    0.67
     currently
    0.67
     actuellement
    0.67
     ongoing
    0.66
    Activations Density 0.294%

    No Known Activations