© 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. 37-GEMMASCOPE-RES-16K
    11. 4519
    Prev
    Next
    INDEX
    Explanations

    scientific measurements and values related to chemical reactions and experimental conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tuyo
    -0.41
     Polda
    -0.39
    @[+][
    -0.38
    lewati
    -0.36
    шься
    -0.35
    ----</
    -0.35
    ➯
    -0.34
     Regierungs
    -0.34
     bordada
    -0.34
    ini
    -0.33
    POSITIVE LOGITS
    ArgsConstructor
    0.68
    脚注の使い方
    0.65
     daß
    0.63
     Cæsar
    0.63
    MemoryWarning
    0.63
    🏽
    0.62
    NameInMap
    0.60
    🏼
    0.59
    🏾
    0.58
     insuffisamment
    0.57
    Activations Density 4.757%

    No Known Activations