© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 210
    Prev
    Next
    INDEX
    Explanations

    key details related to processes, timelines, and significant events in a narrative or factual account

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

    preceding a verb in the past tense

    np_acts-logits-general · gemini-2.0-flash

    officially, formally, seriously

    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
    ReusableCell
    -0.72
     }}"></
    -0.70
     toujours
    -0.66
    outState
    -0.64
     ſtill
    -0.63
     πάντα
    -0.63
    cloudfront
    -0.62
    queryInterface
    -0.61
    tahankan
    -0.60
    argout
    -0.60
    POSITIVE LOGITS
     officially
    1.21
     earnest
    1.19
     formally
    1.17
    本格
    1.16
     seriously
    1.08
    officially
    1.04
    正式
    1.02
     truly
    1.02
     oficialmente
    1.01
     formal
    1.01
    Activations Density 0.534%

    No Known Activations