© 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. 20-GEMMASCOPE-RES-16K
    11. 7375
    Prev
    Next
    INDEX
    Explanations

    the repeated use of articles and common phrases within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     the
    -0.34
     and
    -0.33
     Administrativna
    -0.33
     same
    -0.32
     
    -0.32
    ,
    -0.29
     Whitaker
    -0.28
     advanced
    -0.27
     Whitfield
    -0.27
    <eos>
    -0.26
    POSITIVE LOGITS
     queſto
    0.83
    ſammen
    0.79
    RenderAtEndOf
    0.75
    DockStyle
    0.75
     ويكيپ
    0.74
    abestanden
    0.69
    ᅝ
    0.68
    󰀄
    0.68
    [@BOS@]
    0.67
    <unused52>
    0.67
    Activations Density 3.726%

    No Known Activations