© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12142
    Prev
    Next
    INDEX
    Explanations

    content related to subscribing for updates or newsletters

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

    Email newsletters and subscriptions

    np_acts-logits-general · gemini-2.0-flash

    signing up for newsletters

    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
    rungsseite
    -0.77
    Datuak
    -0.61
     فريبيس
    -0.55
    PYX
    -0.52
     Locally
    -0.52
     Référence
    -0.52
     Dostupné
    -0.51
     Manas
    -0.50
    ->___
    -0.50
     indisponible
    -0.50
    POSITIVE LOGITS
     newsletter
    1.39
     newsletters
    1.23
     Newsletter
    1.23
    newsletter
    1.15
    Newsletter
    1.14
     email
    1.11
     mailing
    1.10
     NEWSLETTER
    1.07
     emails
    1.06
     Email
    0.96
    Activations Density 0.178%

    No Known Activations