© 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. 21-GEMMASCOPE-RES-16K
    6. 13096
    Prev
    Next
    INDEX
    Explanations

    quotes or dialogue from various individuals, indicating statements or perspectives provided in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yourselves
    -0.68
     فريبيس
    -0.61
     themselves
    -0.58
     tutte
    -0.57
     Jurí
    -0.53
     fapt
    -0.53
     inteiro
    -0.52
     tutto
    -0.52
     segreto
    -0.49
     suivantes
    -0.49
    POSITIVE LOGITS
    )"),
    0.96
    })`
    0.92
    )");
    
    0.91
    endphp
    0.89
     spokeswoman
    0.89
    ))));
    0.84
     spokesman
    0.84
    ")));
    
    0.83
    ++]=
    0.80
    ')))
    0.79
    Activations Density 0.108%

    No Known Activations