© 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. 28-GEMMASCOPE-RES-16K
    6. 7815
    Prev
    Next
    INDEX
    Explanations

    references to funding sources and acknowledgments in academic or research contexts

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

    Germany, German, or related terms

    np_acts-logits-general · gemini-2.0-flash

    German Confederation and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bienen
    -0.84
     Stirn
    -0.82
     Wahr
    -0.81
     Liebes
    -0.80
     Wolken
    -0.80
     Mühle
    -0.80
     Leinwand
    -0.79
     Schwert
    -0.77
     Brust
    -0.76
     Schilder
    -0.76
    POSITIVE LOGITS
     Germany
    0.79
     German
    0.73
    Germany
    0.71
    German
    0.63
     germany
    0.63
    ドイツ
    0.63
    Hochspringen
    0.62
     Allemagne
    0.60
     Duitse
    0.58
     Photocase
    0.58
    Activations Density 0.726%

    No Known Activations