© 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. 17-GEMMASCOPE-RES-16K
    11. 446
    Prev
    Next
    INDEX
    Explanations

    statements of intent and communication regarding actions or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dikatakan
    -0.71
    Said
    -0.66
    saying
    -0.65
     mondta
    -0.64
     сказала
    -0.63
     AssemblyProduct
    -0.62
     λέ
    -0.62
     stated
    -0.61
     sayin
    -0.61
     disebutkan
    -0.60
    POSITIVE LOGITS
     aspetta
    0.62
     intende
    0.62
    ContextHolder
    0.58
    URLException
    0.57
     kasarigan
    0.57
    つもり
    0.56
     Chwiliwch
    0.56
     Intent
    0.56
     ***!
    0.55
     hoped
    0.54
    Activations Density 0.257%

    No Known Activations