© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9014
    Prev
    Next
    INDEX
    Explanations

    references to programming concepts, particularly regarding API implementation and functionality

    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
     gewöhnlich
    -0.54
     censiti
    -0.42
     Griechen
    -0.38
    łosi
    -0.37
     voici
    -0.36
     irmã
    -0.36
     reloj
    -0.35
    moveToFirst
    -0.35
     fidé
    -0.35
     graças
    -0.34
    POSITIVE LOGITS
     maybe
    0.71
     perhaps
    0.70
     magari
    0.66
    TypedDataSet
    0.62
    maybe
    0.60
    perhaps
    0.60
     kanske
    0.59
     Maybe
    0.57
    Maybe
    0.56
    Portale
    0.54
    Activations Density 1.062%

    No Known Activations