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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 8715
    Prev
    Next
    INDEX
    Explanations

    references to corporate partnerships and business strategies

    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
    DoubleQuotes
    -0.73
    >');
    -0.51
    }>;
    -0.51
    setVerticalGroup
    -0.47
    SessionFactory
    -0.45
    Искәрмәләр
    -0.44
    ())));
    -0.43
     virtuel
    -0.42
    Spoilers
    -0.41
    abspath
    -0.40
    POSITIVE LOGITS
     business
    1.11
     businesses
    1.07
     Geschäft
    1.07
     negocio
    1.05
    geschäft
    1.01
     portfolio
    0.99
     segment
    0.97
     segments
    0.97
     bisnis
    0.96
     negócio
    0.93
    Activations Density 0.283%

    No Known Activations