© 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. 20-GEMMASCOPE-RES-16K
    11. 2659
    Prev
    Next
    INDEX
    Explanations

    discussions about indigenous populations and their historical contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    historical and anthropological references about indigenous cultures and their technological sophistication.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.54
     propOrder
    -0.52
     Wiktionnaire
    -0.51
    verwijspagina
    -0.51
    iosync
    -0.50
    RTGC
    -0.50
    存于互联网档案馆
    -0.50
    Eucalyptus
    -0.50
    zzleHttp
    -0.50
     Eucalyptus
    -0.49
    POSITIVE LOGITS
     sacerdotes
    0.36
    Derbyniad
    0.35
     penas
    0.33
     primitive
    0.32
    PYX
    0.32
    primitive
    0.31
    TagMode
    0.31
     goda
    0.30
     complex
    0.30
    复杂
    0.29
    Activations Density 0.247%

    No Known Activations