© 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. 11-GEMMASCOPE-RES-16K
    11. 12773
    Prev
    Next
    INDEX
    Explanations

    keywords and concepts related to technology and professional networking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    よう
    -0.46
    μα
    -0.44
     g
    -0.44
    consin
    -0.42
    g
    -0.41
    timos
    -0.41
     devrez
    -0.40
    wasi
    -0.40
     G
    -0.39
     cap
    -0.39
    POSITIVE LOGITS
     Efq
    0.88
     ProtoMessage
    0.85
     ſte
    0.79
     exhibitors
    0.78
     fubject
    0.76
     attendees
    0.76
     perſon
    0.75
     himſelf
    0.75
     ſeveral
    0.74
     ſy
    0.74
    Activations Density 0.113%

    No Known Activations