© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 8947
    Prev
    Next
    INDEX
    Explanations

    phrases indicating advantages and comparisons

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

    "the most" or related superlative phrases

    np_acts-logits-general · gemini-2.0-flash

    the most

    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
     Taktlose
    -0.50
    CloseOperation
    -0.45
    BrowserModule
    -0.44
    cedentes
    -0.44
    enumii
    -0.44
    oredCriteria
    -0.42
    ſelves
    -0.42
    ariales
    -0.41
     betweenstory
    -0.41
     Vikipedi
    -0.41
    POSITIVE LOGITS
     most
    1.70
     biggest
    1.66
     greatest
    1.52
    biggest
    1.52
     가장
    1.49
    最も
    1.39
     najbardziej
    1.36
     самое
    1.35
     наиболее
    1.35
    greatest
    1.34
    Activations Density 0.761%

    No Known Activations