© 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-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 3569
    Prev
    Next
    INDEX
    Explanations

    references to places or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ficult
    -0.56
     gerne
    -0.56
    illoin
    -0.53
     habet
    -0.51
     belangrijke
    -0.51
     sako
    -0.50
     pter
    -0.50
     góp
    -0.50
    ronomy
    -0.49
     Damit
    -0.49
    POSITIVE LOGITS
    seemed
    0.96
     seemed
    0.96
     smelled
    0.86
     reminded
    0.73
    expandindo
    0.70
     surprisingly
    0.69
     consisted
    0.68
     ProtoMessage
    0.67
     resembled
    0.65
     sounded
    0.64
    Activations Density 0.257%

    No Known Activations