© 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. 7312
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and notations related to algebra and functions, especially those involving variables and equations

    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
     Keto
    -0.61
     Keyword
    -0.59
     Kinetic
    -0.55
     Keywords
    -0.55
     Knights
    -0.55
    Keto
    -0.55
     Knowledge
    -0.53
     Kingdom
    -0.52
    Knight
    -0.51
     Keystone
    -0.51
    POSITIVE LOGITS
     k
    2.28
    k
    1.59
     к
    1.30
     ک
    1.03
    k
    0.94
    к
    0.91
     الك
    0.88
    𝑘
    0.84
     הק
    0.83
     क
    0.77
    Activations Density 1.022%

    No Known Activations