© 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. 11326
    Prev
    Next
    INDEX
    Explanations

    words related to physical and emotional responses

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

    followed by prepositions or adverbs

    np_acts-logits-general · gemini-2.0-flash

    ongoing actions and states

    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
     GenerationType
    -0.80
    RegressionTest
    -0.75
     متعلقه
    -0.75
    ="@+
    -0.73
    XmlEnum
    -0.71
     Paglinawan
    -0.71
    IsMutable
    -0.70
    Viitteet
    -0.69
    UnusedPrivate
    -0.68
    mAh
    -0.67
    POSITIVE LOGITS
     out
    0.69
     away
    0.58
     up
    0.57
     down
    0.55
     hard
    0.54
     well
    0.52
     freely
    0.51
     dedans
    0.51
     off
    0.51
     vestiti
    0.50
    Activations Density 0.348%

    No Known Activations