© 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. 4-GEMMASCOPE-RES-16K
    11. 341
    Prev
    Next
    INDEX
    Explanations

    technical terms, code-related keywords, and structured data formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.78
     gynnwys
    -0.78
     "..\..\..\
    -0.74
    writeFieldEnd
    -0.72
    ]._
    -0.69
    estacks
    -0.69
    astéroïdes
    -0.69
     المعيارى
    -0.69
     Efq
    -0.67
     occaf
    -0.66
    POSITIVE LOGITS
    MemoryWarning
    0.81
     beginnetje
    0.77
     pinulongan
    0.73
     Roskov
    0.73
    XmlAccessorType
    0.72
     الاطلاع
    0.71
    matchCondition
    0.71
    تقاوى
    0.70
    
    0.70
    BeginContext
    0.68
    Activations Density 1.047%

    No Known Activations