© 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. 3856
    Prev
    Next
    INDEX
    Explanations

    questions and phrases related to the reasons and mechanisms behind social, medical, or scientific phenomena

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

    phrases that ask "why" something happens, especially in scientific or analytical contexts.

    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
    expandindo
    -0.80
     autorytatywna
    -0.79
    XmlAccessorType
    -0.68
     estekak
    -0.67
    MemoryWarning
    -0.67
     tartalomajánló
    -0.64
    StoryboardSegue
    -0.63
    GTCX
    -0.59
    原始内容存档
    -0.59
     NSCoder
    -0.59
    POSITIVE LOGITS
     why
    0.71
     varför
    0.62
     warum
    0.58
    why
    0.56
     hvorfor
    0.55
     dlaczego
    0.54
    为什么
    0.53
     Warum
    0.50
     pourquoi
    0.50
     Why
    0.49
    Activations Density 0.519%

    No Known Activations