© 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. 23-GEMMASCOPE-RES-16K
    6. 9871
    Prev
    Next
    INDEX
    Explanations

    phrases that describe types or categories of entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     asesino
    -0.54
     oreja
    -0.53
     étrangères
    -0.52
     pembaca
    -0.50
     hendes
    -0.47
     politiet
    -0.47
     étranger
    -0.46
     valiente
    -0.46
     Komunikasi
    -0.46
     avoient
    -0.46
    POSITIVE LOGITS
     sorta
    0.74
     quasi
    0.72
    quasi
    0.68
     sort
    0.67
     akin
    0.63
     Wartawan
    0.59
    المناصب
    0.58
     kind
    0.58
     Sort
    0.56
    instancetype
    0.55
    Activations Density 0.349%

    No Known Activations