© 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-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 5096
    Prev
    Next
    INDEX
    Explanations

    terms related to file management 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 @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     uſed
    -1.07
     myſelf
    -1.01
     uſe
    -0.99
     Theſe
    -0.96
     houſe
    -0.92
     Jefus
    -0.92
     themſelves
    -0.91
    脚注の使い方
    -0.89
    Portale
    -0.88
     fevere
    -0.88
    POSITIVE LOGITS
    CJK
    3.32
     CJK
    0.75
    itemize
    0.61
    arwal
    0.56
    ApiException
    0.55
    enumerate
    0.54
    кси
    0.52
     Cabrera
    0.51
     Jal
    0.50
    undam
    0.48
    Activations Density 0.030%

    No Known Activations