© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 2706
    Prev
    Next
    INDEX
    Explanations

    terms related to management and oversight in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (!__
    -0.66
    windowFixed
    -0.60
     مرئيه
    -0.59
    adaptiveStyles
    -0.59
    WireFormatLite
    -0.58
    XmlSchema
    -0.54
    rebbe
    -0.54
    RTDA
    -0.54
    DockStyle
    -0.54
    protoimpl
    -0.52
    POSITIVE LOGITS
     affairs
    0.94
     finances
    0.90
     destinies
    0.78
     aspects
    0.69
     destiny
    0.68
     relationships
    0.68
     interactions
    0.67
     emotions
    0.66
     assets
    0.66
     movements
    0.65
    Activations Density 0.371%

    No Known Activations