© 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. 11198
    Prev
    Next
    INDEX
    Explanations

    conjunctions and transitional phrases that indicate reasoning or conclusions in scientific discourse

    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
    _;
    -0.54
    ()));
    -0.48
    _,
    -0.46
    ={},
    -0.43
     \%)
    -0.41
     katholischen
    -0.39
    __',
    -0.39
     */,
    -0.39
    ())),
    -0.39
     kuitenkin
    -0.38
    POSITIVE LOGITS
    tanleria
    0.75
    
    0.69
    SequentialGroup
    0.68
     InputDecoration
    0.61
    PerformLayout
    0.61
    kháu
    0.58
    GEBURTSDATUM
    0.58
    دانشنامهٔ
    0.56
     nahilalakip
    0.56
    قایناق‌لار
    0.56
    Activations Density 0.725%

    No Known Activations