© 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. 7367
    Prev
    Next
    INDEX
    Explanations

    references to curfews and restrictions in societal contexts

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

    Comes after words indicating prevention/restriction

    np_acts-logits-general · gemini-2.0-flash

    prevent avoid control against

    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
    GRANTED
    -0.51
    AnchorTagHelper
    -0.51
     prov
    -0.50
     snippetHide
    -0.49
     Automat
    -0.49
    moet
    -0.49
    rungsseite
    -0.48
     Prov
    -0.48
     StatefulWidget
    -0.48
     instr
    -0.48
    POSITIVE LOGITS
     spowod
    0.46
     nedost
    0.46
     často
    0.45
    EndGlobalSection
    0.44
     inimes
    0.44
     indiscriminate
    0.44
     filha
    0.43
    rimônio
    0.43
     muertes
    0.43
     spôso
    0.42
    Activations Density 0.108%

    No Known Activations