© 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. 2-GEMMASCOPE-RES-16K
    6. 13374
    Prev
    Next
    INDEX
    Explanations

    references to compactness and efficiency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.48
     跳转至
    -0.48
    原始内容存档于
    -0.44
    nextLine
    -0.38
     روسيا
    -0.37
    您好
    -0.37
    حوالہ
    -0.36
     Misch
    -0.36
     <>",
    -0.36
    PMailer
    -0.36
    POSITIVE LOGITS
    insert
    0.63
     compact
    0.57
     Compact
    0.57
    Compact
    0.54
     vibrant
    0.54
    Convert
    0.54
    compact
    0.52
     Convert
    0.52
    Portail
    0.51
     polvere
    0.50
    Activations Density 0.254%

    No Known Activations