© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 2718
    Prev
    Next
    INDEX
    Explanations

    references to hidden or secretive elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     بيها
    -0.71
    WindowConstants
    -0.67
    setVerticalGroup
    -0.66
    endphp
    -0.64
    ImageContext
    -0.60
    AdapterView
    -0.57
     initialState
    -0.56
    TagHelper
    -0.55
    anolamine
    -0.55
    utilisons
    -0.55
    POSITIVE LOGITS
     behind
    0.85
     hid
    0.83
     hidden
    0.81
    MethodManager
    0.80
     secrets
    0.79
     secret
    0.76
     hiding
    0.76
     Hidden
    0.74
    Secrets
    0.73
     hide
    0.71
    Activations Density 0.219%

    No Known Activations