© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 12520
    Prev
    Next
    INDEX
    Explanations

    instances and discussions of exchanges or trades

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GHIJKLM
    -0.37
    NOPQRST
    -0.36
    LabelTagHelper
    -0.36
    ėte
    -0.36
    Sov
    -0.34
     vorhanden
    -0.34
    IsContent
    -0.33
    createCell
    -0.33
    larınız
    -0.32
     przesz
    -0.32
    POSITIVE LOGITS
     exchange
    1.55
     EXCHANGE
    1.29
    exchange
    1.28
    Exchange
    1.27
     Exchange
    1.25
     dynamic
    1.17
     exchanged
    1.12
     exchanges
    1.11
    EXCHANGE
    1.05
    dynamic
    1.02
    Activations Density 0.090%

    No Known Activations