© 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. 28-GEMMASCOPE-RES-16K
    11. 4120
    Prev
    Next
    INDEX
    Explanations

    references to family names

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

    Surnames

    np_acts-logits-general · gemini-2.0-flash

    names of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intptr
    -0.57
     thin
    -0.54
    MigrationBuilder
    -0.50
     invokingState
    -0.50
     lenker
    -0.49
    toprule
    -0.49
     DOU
    -0.48
     PRIME
    -0.48
     LAY
    -0.47
     المعيارى
    -0.47
    POSITIVE LOGITS
     predeceased
    0.53
     '\\;'
    0.48
    UnitTesting
    0.40
     honra
    0.39
     honte
    0.39
     preceded
    0.38
     aimez
    0.38
     partager
    0.38
     prénom
    0.38
     omnes
    0.37
    Activations Density 0.040%

    No Known Activations