© 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. 4263
    Prev
    Next
    INDEX
    Explanations

    keywords related to product features and specifications, particularly in digital or promotional contexts

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

    Game, software, or download

    np_acts-logits-general · gemini-2.0-flash

    PC games and software downloads

    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
    WebElementEntity
    -0.59
    #+#
    -0.59
    httphttps
    -0.57
     Infórmanos
    -0.57
     nakalista
    -0.56
     gewöhnlich
    -0.54
    曖昧さ回避
    -0.54
     disponibilités
    -0.54
     kaynağından
    -0.53
     незавершена
    -0.53
    POSITIVE LOGITS
     retro
    0.50
     factory
    0.49
     for
    0.48
     
    0.48
     digital
    0.48
    olu
    0.46
     adult
    0.45
     Hin
    0.45
     Factory
    0.44
     software
    0.44
    Activations Density 0.078%

    No Known Activations