© 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. 38-GEMMASCOPE-RES-16K
    6. 12953
    Prev
    Next
    INDEX
    Explanations

    expressions related to scientific methods and improvements in research techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jefus
    -0.38
     myſelf
    -0.35
    schaft
    -0.33
     $[
    -0.33
    schule
    -0.32
    ',
    
    
    -0.32
     × 
    -0.31
    ՚
    -0.31
     ± 
    -0.31
     < 
    -0.31
    POSITIVE LOGITS
    inthe
    0.84
    ofthe
    0.83
    featureID
    0.82
     ofthe
    0.82
    and
    0.82
    tof
    0.76
    sthe
    0.76
    AndEndTag
    0.76
    untuk
    0.75
    that
    0.74
    Activations Density 1.080%

    No Known Activations