© 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. 4122
    Prev
    Next
    INDEX
    Explanations

    keywords related to legal disclaimers and copyright notices

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

    Text after conjunctions

    np_acts-logits-general · gemini-2.0-flash

    or, so, or, yet

    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
     &
    -0.46
    LookAnd
    -0.38
     iyong
    -0.34
    vateľ
    -0.34
     fieldNum
    -0.33
    ությ
    -0.32
     sonno
    -0.32
    致
    -0.32
    岖
    -0.30
    路
    -0.30
    POSITIVE LOGITS
    expandindo
    0.88
    Kjelder
    0.79
     незавершена
    0.79
    Geplaatst
    0.79
    Externé
    0.73
    URLException
    0.71
    Cyfeiriadau
    0.67
    تقاوى
    0.66
    Bakgrunnsstoff
    0.66
    Spoljašnje
    0.65
    Activations Density 0.490%

    No Known Activations