© 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-2-2B
    7. Residual Stream - 16k
    9. 6-GEMMASCOPE-RES-16K
    11. 5039
    Prev
    Next
    INDEX
    Explanations

    the beginning of documented text or structured segments in legal or formal documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NSCoder
    -1.05
    featureID
    -0.93
     Efq
    -0.88
     myſelf
    -0.87
    webElementXpaths
    -0.87
     poffe
    -0.86
    omock
    -0.85
     occaf
    -0.81
     fubject
    -0.81
     Cæsar
    -0.80
    POSITIVE LOGITS
    <bos>
    0.53
    XmlAccessType
    0.49
    麻
    0.46
    исленность
    0.43
    MemoryWarning
    0.42
    нъ
    0.41
    着
    0.41
    CJK
    0.41
    бно
    0.40
     نم
    0.39
    Activations Density 0.538%

    No Known Activations