© 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. 2405
    Prev
    Next
    INDEX
    Explanations

    references to Sri Lanka and its cultural elements

    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
     plomo
    -0.34
     transition
    -0.32
    Höhe
    -0.31
     enough
    -0.30
     neón
    -0.30
     risk
    -0.30
     qu
    -0.30
     אנו
    -0.30
    minipage
    -0.29
    Điều
    -0.29
    POSITIVE LOGITS
    endpush
    0.71
    MemoryWarning
    0.62
    berdayakan
    0.59
    vastava
    0.56
    writeFieldEnd
    0.56
    IVEREF
    0.51
    TestingModule
    0.51
     JpaRepository
    0.51
    EFIAPI
    0.51
     okuyayım
    0.49
    Activations Density 0.338%

    No Known Activations