© 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. 14973
    Prev
    Next
    INDEX
    Explanations

    positional and directional terms within the context of action or movement

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

    Follows "Q:" or "Guest" (likely question/answer or guest posts)

    np_acts-logits-general · gemini-2.0-flash

    up short

    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
     up
    -0.51
     обра
    -0.51
    álních
    -0.51
     stehenden
    -0.51
    пта
    -0.49
    ']?>
    -0.49
     Mus
    -0.48
    gemene
    -0.48
     U
    -0.47
    uele
    -0.46
    POSITIVE LOGITS
     snippetHide
    0.84
    Vidite
    0.79
     Biôgrafia
    0.74
     للمعارف
    0.72
    ioutil
    0.70
    fjspx
    0.69
    richTextPanel
    0.69
     itſelf
    0.69
    EndGlobalSection
    0.67
    Vorte
    0.67
    Activations Density 0.275%

    No Known Activations