© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 8028
    Prev
    Next
    INDEX
    Explanations

    scientific names and classifications in biological taxonomy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſte
    -0.34
     pro
    -0.29
     ne
    -0.26
     houſe
    -0.24
     da
    -0.23
     brand
    -0.23
     beſt
    -0.23
     ברי
    -0.23
     house
    -0.23
     para
    -0.22
    POSITIVE LOGITS
     ब्रेकडाउन
    1.19
     kasarigan
    1.17
     незавершена
    1.05
     Italijanski
    1.03
    aarrggbb
    1.00
    Diweddarwch
    0.98
    évaluateur
    0.97
    出版年
    0.95
     useAppContext
    0.94
     nahilalakip
    0.92
    Activations Density 0.511%

    No Known Activations