© 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. 0-GEMMASCOPE-RES-16K
    11. 7614
    Prev
    Next
    INDEX
    Explanations

    the name "Jones" and variations of the verb "was" in the context of legal language, specifically related to criminal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kaarangay
    -0.61
     imageNamed
    -0.56
    __*/
    -0.56
    styleable
    -0.54
     termica
    -0.52
     queſta
    -0.52
    moveToNext
    -0.51
     resourceCulture
    -0.51
    astéroïdes
    -0.51
     Administrativna
    -0.50
    POSITIVE LOGITS
     Sus
    0.57
    Sus
    0.48
    PreferredItem
    0.45
    saraba
    0.45
     Li
    0.43
    PM
    0.42
    rt
    0.41
    <!
    0.41
     PyLong
    0.39
     Wa
    0.39
    Activations Density 0.197%

    No Known Activations