© 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. 2915
    Prev
    Next
    INDEX
    Explanations

    instances of the word "admit" in various contexts

    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
     burbujas
    -0.73
     desmotivaciones
    -0.67
     Kollegen
    -0.65
     nôtre
    -0.63
     setempat
    -0.63
     Inscrivez
    -0.63
     llorando
    -0.61
     tasas
    -0.60
     tajam
    -0.60
     deberes
    -0.59
    POSITIVE LOGITS
     charge
    0.69
     cl
    0.68
     plat
    0.67
     outfit
    0.64
     stat
    0.64
     blow
    0.63
     arm
    0.61
     CreateTagHelper
    0.61
     grade
    0.61
     admit
    0.61
    Activations Density 0.227%

    No Known Activations