© 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. 2295
    Prev
    Next
    INDEX
    Explanations

    references to online retrieval and citation formatting

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

    web and internet-related references, URLs, and citations.

    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
     ſche
    -0.65
     betweenstory
    -0.64
    tanleria
    -0.59
     الحره
    -0.58
     iner
    -0.57
    COUVER
    -0.57
     AssemblyCulture
    -0.57
    رشف
    -0.56
     CURIAM
    -0.56
    warts
    -0.55
    POSITIVE LOGITS
    consulté
    1.32
    原始内容存档于
    0.98
     consultato
    0.93
     abgerufen
    0.75
    日閲覧
    0.75
     Процитовано
    0.75
     Consultado
    0.70
    itattu
    0.70
    dostęp
    0.69
    Hozzáférés
    0.67
    Activations Density 0.022%

    No Known Activations