© 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. 5820
    Prev
    Next
    INDEX
    Explanations

    numerical data and technical specifications related to performance metrics

    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
     يتيمه
    -0.81
    }';
    -0.66
    modelBuilder
    -0.64
    findpost
    -0.61
    ]),
    
    -0.60
    ("")]
    
    -0.58
    ximadamente
    -0.58
    %]
    -0.58
    Controllo
    -0.58
    enity
    -0.57
    POSITIVE LOGITS
    a
    1.51
    b
    1.41
    A
    1.29
    B
    1.10
    bis
    0.86
     b
    0.80
    c
    0.78
    а
    0.73
    aA
    0.68
    б
    0.65
    Activations Density 1.472%

    No Known Activations