© 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. 3940
    Prev
    Next
    INDEX
    Explanations

    complex relationships and dependencies in data from various contexts

    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
     Yet
    -0.98
    Yet
    -0.97
     Pourtant
    -0.97
     yet
    -0.90
     entanto
    -0.81
     nevertheless
    -0.81
     pourtant
    -0.81
     however
    -0.80
     However
    -0.80
     pero
    -0.78
    POSITIVE LOGITS
     sondern
    1.69
     hanem
    1.43
     بلکه
    1.42
     אלא
    1.37
     sino
    1.35
    而是
    1.23
     vaan
    1.21
     melainkan
    1.15
     utan
    1.13
     بل
    0.96
    Activations Density 0.225%

    No Known Activations