Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 10721
    Prev
    Next
    INDEX
    Explanations

    mentions of events or actions that highlight political or social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -0.78
     Efq
    -0.73
     itſelf
    -0.69
    rungsseite
    -0.69
     abſ
    -0.68
     ſp
    -0.68
    QtCore
    -0.67
     ſta
    -0.66
     Diſ
    -0.66
     Perſ
    -0.65
    POSITIVE LOGITS
    prefixer
    0.57
    //</
    0.50
    ThroughAttribute
    0.50
     jonka
    0.49
    帖最后由
    0.49
    -------------</
    0.48
    /**
    0.47
     versteht
    0.46
    extends
    0.45
    /******/
    0.45
    Activations Density 0.146%

    No Known Activations