© 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. 2-GEMMASCOPE-RES-16K
    6. 9175
    Prev
    Next
    INDEX
    Explanations

    references to teams or groups, particularly in a competitive context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    JNIEnv
    -0.44
    addGap
    -0.41
     فريبيس
    -0.41
    pageY
    -0.41
    jsxFileName
    -0.40
    
    -0.40
     Nobel
    -0.40
    XmlAccessorType
    -0.40
    
    
    -0.39
    toprule
    -0.39
    POSITIVE LOGITS
     squad
    1.77
     tribe
    1.70
     crew
    1.63
     gang
    1.50
     troupe
    1.49
     fleet
    1.47
     herd
    1.44
     flock
    1.42
     squads
    1.39
    squad
    1.38
    Activations Density 0.292%

    No Known Activations