© 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. 10-GEMMASCOPE-RES-16K
    6. 7749
    Prev
    Next
    INDEX
    Explanations

    terminology related to smart technology and intelligent devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     passagem
    -0.36
    addPreferredGap
    -0.35
     separado
    -0.35
     sépar
    -0.34
     ressemb
    -0.34
     entirely
    -0.34
     Ríos
    -0.34
     earlier
    -0.33
     Misalnya
    -0.33
     separate
    -0.33
    POSITIVE LOGITS
     Smart
    1.92
     smart
    1.91
    smart
    1.84
    Smart
    1.84
     SMART
    1.74
    SMART
    1.70
     smartest
    1.58
     smarter
    1.53
     Intelligent
    1.48
    Intelligent
    1.47
    Activations Density 0.134%

    No Known Activations