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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 1450
    Prev
    Next
    INDEX
    Explanations

    references to installation processes and procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Notae
    -0.63
     CURIAM
    -0.63
    PyExc
    -0.59
    MessageOf
    -0.57
     الرياضيه
    -0.57
    IActionResult
    -0.57
    awaiter
    -0.56
    NAD
    -0.56
     RIPRODUZIONE
    -0.54
    RectangleBorder
    -0.54
    POSITIVE LOGITS
     installation
    1.05
     installations
    0.99
     install
    0.96
     Install
    0.95
    Install
    0.94
     Installation
    0.94
     installed
    0.92
     Installations
    0.90
     INSTALL
    0.88
     Installed
    0.88
    Activations Density 0.119%

    No Known Activations