© 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. 10545
    Prev
    Next
    INDEX
    Explanations

    references to biological or procedural topics related to medical and scientific contexts

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

    relating to business, science, medicine

    np_acts-logits-general · gemini-2.0-flash

    regarding or concerning

    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
     osz
    -0.40
    GIVEREF
    -0.40
     twice
    -0.40
     koos
    -0.39
     fates
    -0.39
     cleverly
    -0.38
     بص
    -0.38
     WITHOUT
    -0.38
    ographically
    -0.38
     hộ
    -0.38
    POSITIVE LOGITS
     regarding
    1.22
    regarding
    1.05
    Regarding
    1.04
     concerning
    1.02
     Regarding
    0.97
    Concerning
    0.94
     щодо
    0.94
     terhadap
    0.94
     concernant
    0.89
     Concerning
    0.89
    Activations Density 1.006%

    No Known Activations