© 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. 15-GEMMASCOPE-RES-16K
    6. 2044
    Prev
    Next
    INDEX
    Explanations

    expressions of laughter or amusement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    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
    -0.84
    AddHtmlAttribute
    -0.74
    __':
    
    -0.73
    +#+#
    -0.72
    __":
    
    -0.71
     INTERESAR
    -0.67
     StatefulWidget
    -0.67
    mybatisplus
    -0.65
    ArgsConstructor
    -0.65
    __":
    -0.65
    POSITIVE LOGITS
    Mmmm
    0.34
    oo
    0.34
    Mmm
    0.33
    Ah
    0.31
     Mmm
    0.30
    !
    0.30
     thus
    0.30
    Hmm
    0.28
     yay
    0.28
    ooo
    0.28
    Activations Density 0.143%

    No Known Activations