© 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. 453
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references related to court cases and proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to legal terms and actions

    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
    的一天
    -0.52
      
    -0.50
    bü
    -0.46
    .
    -0.43
    ↵↵
    -0.42
    艸
    -0.42
     var
    -0.42
     «
    -0.42
       
    -0.41
    책
    -0.41
    POSITIVE LOGITS
     Efq
    1.13
     itſelf
    1.10
     myſelf
    1.05
    ſelf
    1.01
    ]")]
    0.96
     Majefty
    0.94
     Jefus
    0.90
    ſelves
    0.90
     himſelf
    0.90
     typelib
    0.87
    Activations Density 1.460%

    No Known Activations