© 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. 30-GEMMASCOPE-RES-16K
    11. 10711
    Prev
    Next
    INDEX
    Explanations

    references to distinct components and sections within a larger whole

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

    "parts/aspects/portions of"

    np_acts-logits-general · gemini-2.0-flash

    aspects of; parts of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     instance
    -0.29
     wię
    -0.27
     kancel
    -0.27
    </em>
    -0.27
    Providers
    -0.27
    dropIfExists
    -0.27
    FACTORY
    -0.26
     サイ
    -0.26
     oficina
    -0.26
     example
    -0.26
    POSITIVE LOGITS
    TypedDataSet
    0.74
    новништво
    0.68
     portions
    0.66
    بوابة
    0.63
    ValueStyle
    0.62
    حياته
    0.62
    Tikang
    0.62
     estekak
    0.61
    Portion
    0.60
    StoryboardSegue
    0.60
    Activations Density 0.388%

    No Known Activations