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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9167
    Prev
    Next
    INDEX
    Explanations

    historical references related to immigration and settlement

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

    about people arriving or moving

    np_acts-logits-general · gemini-2.0-flash

    arrival of settlers

    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
     tilbage
    -0.39
     salão
    -0.38
     ubicado
    -0.36
     located
    -0.36
     ovunque
    -0.36
    indest
    -0.35
    了出去
    -0.35
     suất
    -0.34
     near
    -0.34
     thuis
    -0.34
    POSITIVE LOGITS
     arriving
    1.71
     arrival
    1.52
     arrived
    1.50
     arrive
    1.48
     arrives
    1.48
     arrivals
    1.40
    arrival
    1.37
     Arrival
    1.30
    Arri
    1.29
    Arrival
    1.29
    Activations Density 0.549%

    No Known Activations