© 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 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. 5960
    Prev
    Next
    INDEX
    Explanations

    instances of violence and responsibility in political contexts

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

    Text after apostrophes

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions

    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
     Tamb
    -0.40
     dri
    -0.39
     unnecessarily
    -0.36
    manual
    -0.36
    Рек
    -0.36
     layui
    -0.36
    MANUAL
    -0.35
     اص
    -0.35
     voluntarily
    -0.35
    drive
    -0.35
    POSITIVE LOGITS
     disambiguazione
    0.74
    NameInMap
    0.63
    
    0.60
    HasForeignKey
    0.52
     ujednoznacz
    0.49
    homonymie
    0.49
     الحره
    0.48
    fillType
    0.47
    fastjson
    0.47
    rawDesc
    0.46
    Activations Density 0.099%

    No Known Activations