© 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. 25-GEMMASCOPE-RES-16K
    11. 15032
    Prev
    Next
    INDEX
    Explanations

    references to book purchases and limited editions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     high
    -0.36
     animal
    -0.36
     protein
    -0.36
     food
    -0.35
     poultry
    -0.33
     human
    -0.33
     app
    -0.33
    ('');
    -0.33
     grass
    -0.32
     Human
    -0.32
    POSITIVE LOGITS
     exemplaire
    0.79
     copies
    0.71
     exemplaires
    0.68
     Copies
    0.65
     ejemplares
    0.64
    DockStyle
    0.63
     copias
    0.62
     экзем
    0.61
     ejemplar
    0.60
    copies
    0.59
    Activations Density 0.727%

    No Known Activations