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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 15189
    Prev
    Next
    INDEX
    Explanations

    italicized and bold text formatting tags

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.71
     
    -0.68
    DockStyle
    -0.68
     NavController
    -0.66
    SafeAreaView
    -0.63
     ResponseEntity
    -0.59
    endregion
    -0.59
     baweł
    -0.58
     IERC
    -0.57
     BaseController
    -0.57
    POSITIVE LOGITS
    <i>
    1.30
    <em>
    1.21
    </i>
    0.75
    /*
    0.75
    </em>
    0.67
    __(/*!
    0.66
    <u>
    0.59
    /*
    0.59
    《
    0.58
    italic
    0.57
    Activations Density 0.153%

    No Known Activations