© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 9367
    Prev
    Next
    INDEX
    Explanations

    adjectives that describe negativity or wrongdoing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCompany
    -0.49
    atom
    -0.47
     picioare
    -0.46
     Curl
    -0.46
     aé
    -0.46
     fó
    -0.45
     viață
    -0.45
    testens
    -0.45
     ViewHolder
    -0.44
     ſind
    -0.44
    POSITIVE LOGITS
    ous
    0.70
    ious
    0.65
    OUS
    0.61
    ously
    0.60
    uous
    0.59
    Wil
    0.58
    IOUS
    0.57
    UOUS
    0.55
    GraphicsUnit
    0.55
     Wil
    0.54
    Activations Density 0.263%

    No Known Activations