© 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. 8039
    Prev
    Next
    INDEX
    Explanations

    inquiries about needs and assistance, particularly in educational and organizational contexts

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

    Followed by a question mark or suggesting a need

    np_acts-logits-general · gemini-2.0-flash

    looking for something

    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
     חיצוניים
    -0.73
    addGap
    -0.71
     HasFactory
    -0.67
     שוליים
    -0.65
    ########.
    -0.60
    schedulers
    -0.58
    Réponse
    -0.57
     विश्वसनीयता
    -0.57
     Drapeau
    -0.56
     ostavi
    -0.55
    POSITIVE LOGITS
     want
    1.76
     Want
    1.71
     wanting
    1.68
    Want
    1.62
    want
    1.60
     WANT
    1.34
     desiring
    1.32
     wishing
    1.28
     wants
    1.27
     interested
    1.25
    Activations Density 0.169%

    No Known Activations