© 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-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 10987
    Prev
    Next
    INDEX
    Explanations

    expressions of compassion and empathy towards vulnerable groups, particularly refugees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -0.74
     purpoſe
    -0.71
     Anſ
    -0.67
     Reſ
    -0.66
     itſelf
    -0.62
     Theſe
    -0.61
    nos
    -0.61
     Excited
    -0.60
     Beſ
    -0.60
     Amalgam
    -0.59
    POSITIVE LOGITS
    CPtr
    0.65
    adaptiveStyles
    0.61
    enterOuterAlt
    0.61
    expandindo
    0.56
     resourceCulture
    0.54
     propOrder
    0.53
     nawr
    0.53
     noDo
    0.52
    ActionCreators
    0.52
     ExecuteAsync
    0.51
    Activations Density 0.260%

    No Known Activations