© 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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 31765
    Prev
    Next
    INDEX
    Explanations

    words associated with disabling or turning off functionalities, particularly in a technical or programming context

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    disabling features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Архів
    -0.65
    mobileqq
    -0.63
    DidLoad
    -0.63
    ்ச
    -0.60
    袱
    -0.59
    s
    -0.58
    جوايز
    -0.58
     magasiner
    -0.58
    айт
    -0.58
    nyez
    -0.57
    POSITIVE LOGITS
    ])):
    0.94
     Basse
    0.84
     paraly
    0.82
    theless
    0.79
     disabling
    0.79
     disables
    0.79
    ']));
    0.77
    })));
    0.75
    ]]:
    0.74
     }));
    0.73
    Activations Density 0.022%

    No Known Activations