© 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. 4148
    Prev
    Next
    INDEX
    Explanations

    references to internal processes or elements in a variety of contexts

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

    "internal" and its related forms

    np_acts-logits-general · gemini-2.0-flash

    internal contexts

    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
     للمعارف
    -0.84
    GEBURTSDATUM
    -0.73
    MessageOf
    -0.66
     autorytatywna
    -0.64
    parsedMessage
    -0.64
     pleaſure
    -0.62
    titleMargin
    -0.60
     ujednoznacz
    -0.60
    Демографія
    -0.59
    PMailer
    -0.59
    POSITIVE LOGITS
     internal
    1.13
     Internal
    1.11
    Internal
    1.10
    internal
    1.02
     INTERNAL
    0.95
    INTERNAL
    0.94
     internally
    0.86
    内
    0.75
    内部
    0.71
     inside
    0.69
    Activations Density 0.166%

    No Known Activations