© 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. 3-GEMMASCOPE-RES-16K
    11. 6856
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    argout
    -0.87
    isDebugEnabled
    -0.86
     ISNI
    -0.84
     HttpHeaders
    -0.81
     mignon
    -0.80
    WithIOException
    -0.78
    DataBean
    -0.78
    HttpHeaders
    -0.78
    تفصیلات
    -0.76
    期刊论文
    -0.74
    POSITIVE LOGITS
     place
    2.89
    place
    2.83
    Place
    2.74
     PLACE
    2.64
     Place
    2.63
     places
    2.62
    places
    2.54
    PLACE
    2.47
    Places
    2.46
     Places
    2.42
    Activations Density 0.037%

    No Known Activations