© 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. 4358
    Prev
    Next
    INDEX
    Explanations

    technical or programming terms and elements related to coding operations

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

    Auxiliary verbs/modals (will, should, would, etc)

    np_acts-logits-general · gemini-2.0-flash

    adequate or sufficient

    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
    windowFixed
    -0.47
     Rodrig
    -0.45
    ualaikum
    -0.42
    GIVEREF
    -0.41
     puro
    -0.39
    kabau
    -0.39
    IonicModule
    -0.38
     Assembly
    -0.38
     ſch
    -0.37
    lankton
    -0.37
    POSITIVE LOGITS
     suffice
    1.27
     suffices
    1.27
     suffic
    1.10
     sufficient
    0.93
     adequate
    0.87
     satisfactory
    0.83
     acceptable
    0.81
     suffit
    0.81
     Sufficient
    0.81
    Sufficient
    0.79
    Activations Density 0.434%

    No Known Activations