© 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. 37-GEMMASCOPE-RES-16K
    11. 6122
    Prev
    Next
    INDEX
    Explanations

    key phrases that indicate primary or significant aspects of a topic or argument

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Situation
    -0.38
     situatie
    -0.38
     tertentu
    -0.37
    |')
    -0.37
    avier
    -0.37
     Situ
    -0.36
     Situation
    -0.36
     кӀ
    -0.35
     mere
    -0.35
    Situ
    -0.35
    POSITIVE LOGITS
     focus
    0.89
     contributor
    0.85
     contributors
    0.85
     concern
    0.82
     driver
    0.76
     culprit
    0.76
    stays
    0.76
     beneficiaries
    0.73
     culprits
    0.73
     reason
    0.72
    Activations Density 0.463%

    No Known Activations