© 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. 8180
    Prev
    Next
    INDEX
    Explanations

    key terms and phrases related to programming and model loading in machine learning

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

    Tokens before numbers

    np_acts-logits-general · gemini-2.0-flash

    and verification or genetic record

    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
     Brooks
    -0.36
     thread
    -0.36
    ợ
    -0.34
     Schen
    -0.34
     Oppen
    -0.34
    thread
    -0.33
     construction
    -0.33
     Wille
    -0.32
    anchor
    -0.32
     Renaud
    -0.31
    POSITIVE LOGITS
    AndEndTag
    0.66
     المعيارى
    0.64
    SourceChecksum
    0.62
     classifying
    0.60
    الحياه
    0.60
    TagMode
    0.59
    IBOutlet
    0.57
     bluzka
    0.55
     Roskov
    0.55
    httphttps
    0.54
    Activations Density 0.203%

    No Known Activations