© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 11452
    Prev
    Next
    INDEX
    Explanations

    specific punctuation and formatting elements in text passages

    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
     CURIAM
    -0.40
     bon
    -0.40
    XmlAccessorType
    -0.39
     Bon
    -0.38
     mvc
    -0.36
     bat
    -0.36
     EdgeInsets
    -0.36
     tab
    -0.36
     EClass
    -0.35
    WireFormatLite
    -0.35
    POSITIVE LOGITS
    jména
    0.73
     itſelf
    0.71
     pleaſure
    0.67
     المعيارى
    0.66
     للاسماء
    0.65
     indígen
    0.65
     yoksa
    0.65
    ſelf
    0.64
    期刊论文
    0.63
     poffible
    0.63
    Activations Density 1.008%

    No Known Activations