© 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-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 4845
    Prev
    Next
    INDEX
    Explanations

    references to safety regulations and standards in construction or industrial contexts

    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
     sabbat
    -0.65
     hosped
    -0.64
    ificity
    -0.59
     bottling
    -0.57
     traduc
    -0.57
     ironically
    -0.56
    thanks
    -0.55
    GROW
    -0.54
     THINGS
    -0.53
    hosted
    -0.53
    POSITIVE LOGITS
     рекомендуется
    0.62
     skall
    0.61
     preferably
    0.60
    ütfen
    0.60
     segar
    0.59
    又は
    0.58
     shall
    0.57
     conformément
    0.56
     نباید
    0.56
     varsa
    0.56
    Activations Density 0.705%

    No Known Activations