© 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. 6261
    Prev
    Next
    INDEX
    Explanations

    references to "key" in various contexts, particularly in relation to security and input devices

    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
    GraphicsUnit
    -0.99
    expandindo
    -0.81
    IVEREF
    -0.77
    addCriterion
    -0.76
    ContentAsync
    -0.73
     Viitattu
    -0.70
    webElementXpaths
    -0.69
    Autoritní
    -0.69
     linkovi
    -0.69
     مصرى
    -0.69
    POSITIVE LOGITS
     keys
    0.86
    hole
    0.84
     key
    0.84
     Keys
    0.80
     Key
    0.79
    keys
    0.77
     KEY
    0.77
     fob
    0.76
    stroke
    0.75
    key
    0.75
    Activations Density 0.070%

    No Known Activations