© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 15206
    Prev
    Next
    INDEX
    Explanations

    phrases related to artistic talent and skill, particularly in performance arts

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

    "modern" or related foreign-language words

    np_acts-logits-general · gemini-2.0-flash

    modern or contemporary periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fermée
    -0.36
     nozze
    -0.35
     Previously
    -0.35
     balení
    -0.33
     wcześniej
    -0.33
     sebelumnya
    -0.32
     zuvor
    -0.31
     anfangs
    -0.31
     zunächst
    -0.30
    Previously
    -0.30
    POSITIVE LOGITS
     modern
    2.78
    modern
    2.48
     MODERN
    2.23
    Modern
    2.23
     Modern
    2.19
     contemporary
    2.16
     moderne
    2.14
    现代
    2.13
     moderno
    2.11
     modernen
    2.11
    Activations Density 0.570%

    No Known Activations