© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 5585
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific and technical concepts, particularly in nanotechnology and ecological studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dyna
    -0.52
     pumps
    -0.50
    writeField
    -0.48
    InSection
    -0.48
    Full
    -0.48
     Full
    -0.47
     full
    -0.46
    AnchorStyles
    -0.46
    万年
    -0.45
    PRNewswire
    -0.45
    POSITIVE LOGITS
    RTLR
    0.50
     ProtoMessage
    0.45
     AdapterView
    0.43
    таратура
    0.43
    romolecules
    0.41
     footwear
    0.41
    romole
    0.40
    aarrggbb
    0.40
    ัตว์
    0.40
     Wicidata
    0.40
    Activations Density 2.259%

    No Known Activations