© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 467
    Prev
    Next
    INDEX
    Explanations

    references to self and personal perspective in discussions

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

    Follows "i.e." or "e.g."

    np_acts-logits-general · gemini-2.0-flash

    i.e. or e.g

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "]);
    
    -0.56
    }
    
    
    -0.51
     })}
    -0.50
    ']")
    -0.49
     zum
    -0.49
    queryInterface
    -0.48
    商品説明
    -0.48
    "]/
    -0.47
     }}$.
    -0.47
    ]$}
    -0.47
    POSITIVE LOGITS
     e
    1.01
    e
    0.87
    ConstraintMaker
    0.74
     kasarigan
    0.70
    ReusableCell
    0.70
    elizabeth
    0.70
    setVerticalGroup
    0.69
    
    0.68
     eg
    0.66
     JpaRepository
    0.64
    Activations Density 0.188%

    No Known Activations