© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 5740
    Prev
    Next
    INDEX
    Explanations

    sequences that indicate temporal relationships and connections between events or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.45
     MainAxisSize
    -0.45
    inghouse
    -0.40
    %)$
    -0.39
     OFDb
    -0.38
    hyrchwyd
    -0.38
     Vik
    -0.37
    ceptor
    -0.37
    ABLO
    -0.37
    quedas
    -0.37
    POSITIVE LOGITS
     next
    0.69
     nästa
    0.65
    next
    0.62
     prochaine
    0.56
     NEXT
    0.55
    下一个
    0.54
     Next
    0.54
    webElementXpaths
    0.54
     nächste
    0.53
     kế
    0.52
    Activations Density 0.576%

    No Known Activations