© 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. 4687
    Prev
    Next
    INDEX
    Explanations

    phrases indicating places of origin or significance

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

    Following "of" in various contexts

    np_acts-logits-general · gemini-2.0-flash

    of followed by a named entity or concept

    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
     الجمه
    -0.40
     scene
    -0.37
    UseVisualStyle
    -0.36
     represented
    -0.35
     storica
    -0.35
     prá
    -0.33
     visited
    -0.33
     behaved
    -0.33
     zufolge
    -0.33
     geschlossen
    -0.33
    POSITIVE LOGITS
     betweenstory
    0.64
    UrlResolution
    0.61
     հղումներ
    0.60
     kaarangay
    0.60
    хьтан
    0.57
     चीज़ों
    0.56
     '{@
    0.54
    InputBorder
    0.52
    richTextPanel
    0.52
    PostInfinity
    0.51
    Activations Density 0.250%

    No Known Activations