© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 8387
    Prev
    Next
    INDEX
    Explanations

    intensifiers that emphasize degrees of comparison or particularity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     integridad
    -0.48
    zeitige
    -0.40
     dispuesto
    -0.38
     ciudadanía
    -0.38
     préstamos
    -0.37
    ähteet
    -0.37
     związane
    -0.36
    出版年
    -0.36
     herencia
    -0.36
     zwią
    -0.35
    POSITIVE LOGITS
    AnchorStyles
    0.63
     للاسماء
    0.63
     extremely
    0.60
     low
    0.52
     improved
    0.52
    EDEFAULT
    0.52
    clientY
    0.51
    IntoConstraints
    0.49
     exceptionally
    0.49
    الحياه
    0.49
    Activations Density 0.657%

    No Known Activations