© 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. 33-GEMMASCOPE-RES-16K
    11. 928
    Prev
    Next
    INDEX
    Explanations

    HTML tags and formatting elements in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <em>
    -0.88
    </em>
    -0.74
    er
    -0.64
    ة
    -0.64
    an
    -0.63
    </strong>
    -0.62
    ان
    -0.61
    es
    -0.54
    <strong>
    -0.52
    ות
    -0.52
    POSITIVE LOGITS
    </i>
    0.71
     \\
    0.65
    VYMaps
    0.62
    </b>
    0.57
     kaarangay
    0.50
     wireType
    0.48
    JsonInclude
    0.47
    
    0.47
    bibfield
    0.44
     Arxivat
    0.44
    Activations Density 0.131%

    No Known Activations