© 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. 27-GEMMASCOPE-RES-16K
    11. 9712
    Prev
    Next
    INDEX
    Explanations

    instances of tension or conflict, particularly those linked to relationships and disputes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.57
    finity
    -0.47
     queſta
    -0.47
    LLocation
    -0.46
    renda
    -0.46
     nakalista
    -0.45
     cucchiai
    -0.45
     חיצוניים
    -0.45
    Knock
    -0.43
     capac
    -0.43
    POSITIVE LOGITS
     conflict
    1.36
     conflicts
    1.30
     tensions
    1.25
     disputes
    1.23
     dispute
    1.12
     Conflict
    1.10
    conflict
    1.09
     clashes
    1.07
     konflik
    1.06
     disagreements
    1.06
    Activations Density 0.684%

    No Known Activations