© 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. 30-GEMMASCOPE-RES-16K
    11. 10927
    Prev
    Next
    INDEX
    Explanations

    instances of social interactions and connections between individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Relating or referring to other individuals

    np_acts-logits-general · gemini-2.0-flash

    people and their relations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -0.68
     typelib
    -0.66
    RegressionTest
    -0.65
     ब्रेकडाउन
    -0.64
    reportWebVitals
    -0.61
    uxxxx
    -0.59
    WriteTagHelper
    -0.58
     ivelany
    -0.57
    aarrggbb
    -0.56
     SafeMath
    -0.56
    POSITIVE LOGITS
     strangers
    0.73
     fellow
    0.71
     peers
    0.65
     sesama
    0.60
     colleagues
    0.56
     others
    0.55
     someone
    0.53
     whome
    0.52
     friends
    0.50
     eachother
    0.50
    Activations Density 0.427%

    No Known Activations