Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 5721
    Prev
    Next
    INDEX
    Explanations

    key financial metrics and indicators related to government credit ratings and forecasts

    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
    SequentialGroup
    -0.46
    providedIn
    -0.45
    ByVersion
    -0.45
     怎样
    -0.44
    httphttps
    -0.43
    ◹
    -0.41
    Gön
    -0.40
     Bookings
    -0.40
     schi
    -0.40
     Scripts
    -0.40
    POSITIVE LOGITS
     ratings
    0.88
     rating
    0.87
     Ratings
    0.80
     downgrade
    0.79
     Rating
    0.75
    Ratings
    0.74
     downg
    0.72
    ratings
    0.71
     RATING
    0.71
     downgraded
    0.71
    Activations Density 0.195%

    No Known Activations