© 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. 0-GEMMASCOPE-RES-16K
    11. 3121
    Prev
    Next
    INDEX
    Explanations

    references to previous relationships or entities, particularly those denoted by the prefix "ex."

    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
     pleaſure
    -0.83
     indígen
    -0.71
     themſelves
    -0.68
     myſelf
    -0.66
     ſont
    -0.66
     étoit
    -0.65
     desmotivaciones
    -0.65
     koszulka
    -0.65
     leaſt
    -0.64
     saveiro
    -0.64
    POSITIVE LOGITS
     former
    0.92
    former
    0.77
     Former
    0.71
     ex
    0.69
    Former
    0.60
     formerly
    0.59
     season
    0.57
    月
    0.52
    formerly
    0.51
    previous
    0.50
    Activations Density 0.574%

    No Known Activations