© 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. 7030
    Prev
    Next
    INDEX
    Explanations

    expressions related to physical discomfort or reactions

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

    Follows "was," "is," or similar state-of-being verbs

    np_acts-logits-general · gemini-2.0-flash

    sudden change of state

    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
     sometimes
    -0.68
     geleg
    -0.63
     ibland
    -0.63
    Jeografia
    -0.62
     consistently
    -0.62
     spesso
    -0.62
    sometimes
    -0.60
     occasionally
    -0.59
     parfois
    -0.59
    偶尔
    -0.58
    POSITIVE LOGITS
     momentarily
    0.67
     momentary
    0.66
     immediate
    0.65
     seconds
    0.62
    tagHelperRunner
    0.62
     sudden
    0.61
     Immediate
    0.57
     suddenly
    0.56
     Suddenly
    0.56
    さっき
    0.55
    Activations Density 0.290%

    No Known Activations