© 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. 18-GEMMASCOPE-RES-16K
    11. 10686
    Prev
    Next
    INDEX
    Explanations

    critical terms or concepts that emphasize key points or requirements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "key" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    key followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    complexContent
    -0.74
     intptr
    -0.68
    errHandler
    -0.68
    adaptiveStyles
    -0.66
    homonymie
    -0.65
    CPtr
    -0.65
    ftagPool
    -0.64
    ьаж
    -0.64
     CreateTagHelper
    -0.62
    ResponseWriter
    -0.60
    POSITIVE LOGITS
     key
    0.71
     players
    0.67
     ingredient
    0.66
     player
    0.66
     factor
    0.63
     Key
    0.60
     component
    0.60
    hole
    0.59
     role
    0.58
    noted
    0.57
    Activations Density 0.220%

    No Known Activations