© 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. 16-GEMMASCOPE-RES-16K
    11. 13237
    Prev
    Next
    INDEX
    Explanations

    conditional phrases indicating purpose or outcome

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

    Followed by a modal verb

    np_acts-logits-general · gemini-2.0-flash

    so that followed by pronoun and verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleaſure
    -0.87
     ſtate
    -0.75
     Jefus
    -0.73
     Monfieur
    -0.70
     quæ
    -0.69
     ſch
    -0.69
     ſche
    -0.68
     eventName
    -0.67
     Majefty
    -0.67
     chofe
    -0.64
    POSITIVE LOGITS
     puissiez
    0.90
     easier
    0.65
     supaya
    0.63
     better
    0.62
    easier
    0.59
    Easier
    0.58
     möglichst
    0.58
     avoid
    0.57
     biar
    0.55
    bildeten
    0.55
    Activations Density 0.128%

    No Known Activations