© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 9472
    Prev
    Next
    INDEX
    Explanations

    terms associated with technology and computer systems

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    }))
    
    -0.75
     تضيفلها
    -0.74
    }));
    
    -0.65
    __":
    -0.63
     ligiloj
    -0.62
    MLLoader
    -0.62
    )$}
    -0.60
    ]$}
    -0.60
    Παραπομπές
    -0.58
    ]));
    
    -0.58
    POSITIVE LOGITS
     privato
    0.52
     pubblici
    0.49
    าย
    0.47
     незавершена
    0.46
     fears
    0.46
     Rtl
    0.46
     MotionEvent
    0.45
    ogos
    0.45
     giudi
    0.45
    AddHtmlAttribute
    0.44
    Activations Density 0.803%

    No Known Activations