© 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. 23-GEMMASCOPE-RES-16K
    11. 2735
    Prev
    Next
    INDEX
    Explanations

    references to laboratories and associated environments or activities

    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
    Pisces
    -0.50
    Peso
    -0.47
    stick
    -0.45
    Bitcoin
    -0.44
     Bitcoin
    -0.44
     JNI
    -0.44
     Wheat
    -0.44
    wheat
    -0.43
     Bö
    -0.43
    PostBack
    -0.43
    POSITIVE LOGITS
     Administrativna
    0.70
     studio
    0.70
     FACTORY
    0.69
     studios
    0.66
     atelier
    0.66
     initComponents
    0.66
    FACTORY
    0.65
     Studio
    0.65
    studio
    0.65
     Factory
    0.65
    Activations Density 0.335%

    No Known Activations