© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 14663
    Prev
    Next
    INDEX
    Explanations

    specific scientific notations, statistical results, and genetic measurements in research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     McMillan
    -0.59
     Lozano
    -0.54
     Figue
    -0.53
     Ashby
    -0.50
     Beauchamp
    -0.49
     Lockwood
    -0.49
     Bloomfield
    -0.48
     Schrö
    -0.48
     Kline
    -0.47
     Valladolid
    -0.45
    POSITIVE LOGITS
     Kelley
    0.59
     Cunha
    0.59
     Corbett
    0.59
    الحياه
    0.58
     Spenser
    0.58
     betweenstory
    0.57
     Winfrey
    0.57
     Sidd
    0.56
     Gaud
    0.56
     Smyth
    0.54
    Activations Density 1.424%

    No Known Activations