© 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. 7-GEMMASCOPE-RES-16K
    11. 4782
    Prev
    Next
    INDEX
    Explanations

    details about specific individuals or events related to announcements or news articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Enllaces
    -0.58
     particulares
    -0.56
    FormState
    -0.55
     chale
    -0.55
     препратки
    -0.52
     فريبيس
    -0.52
     око
    -0.49
     disiplin
    -0.48
    Earth
    -0.48
    UrlEncoded
    -0.48
    POSITIVE LOGITS
    脚注の使い方
    0.64
    :+:
    0.64
    تقاوى
    0.63
     peacock
    0.55
    complexContent
    0.54
     news
    0.54
    Tikang
    0.53
    jspx
    0.53
    mybatisplus
    0.53
    findpost
    0.52
    Activations Density 0.256%

    No Known Activations