© 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. 15-GEMMASCOPE-RES-16K
    11. 3045
    Prev
    Next
    INDEX
    Explanations

    phrases related to substitutions or replacements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portály
    -0.46
    出版年
    -0.41
     Associated
    -0.41
     plie
    -0.40
    nasel
    -0.40
    addContainerGap
    -0.39
    RTLU
    -0.39
    AndEndTag
    -0.38
    TypedDataSet
    -0.38
     Camp
    -0.38
    POSITIVE LOGITS
     replaced
    1.18
     replace
    1.16
     replacement
    1.14
     replacements
    1.11
     Replace
    1.09
     replacing
    1.08
    replaced
    1.07
     substitutes
    1.05
     replaces
    1.04
     substitute
    1.03
    Activations Density 0.605%

    No Known Activations