© 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. 39-GEMMASCOPE-RES-16K
    11. 671
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "the" and recurring elements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/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.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.64
     myſelf
    -0.56
     najbolj
    -0.48
    ngOn
    -0.48
    izoen
    -0.47
     moſt
    -0.47
    最好的
    -0.47
     bäst
    -0.46
     Theſe
    -0.46
     okuyayım
    -0.46
    POSITIVE LOGITS
     fact
    1.68
     Tatsache
    1.38
     faptul
    1.20
     lack
    1.14
    fact
    1.08
     feit
    1.02
     sheer
    0.96
     hecho
    0.92
     absence
    0.90
     enormous
    0.90
    Activations Density 0.903%

    No Known Activations