© 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 EvalsExportsAPI 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. 5524
    Prev
    Next
    INDEX
    Explanations

    references to assistance or help in 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
     Ausgang
    -0.58
     disambiguazione
    -0.54
    Tikang
    -0.54
     dessus
    -0.44
    endforeach
    -0.44
    ropia
    -0.43
    htra
    -0.42
    LookUp
    -0.42
    nationality
    -0.42
    OGEN
    -0.41
    POSITIVE LOGITS
     arrive
    3.00
     arrives
    2.90
     arrived
    2.89
     arrival
    2.85
     arriving
    2.76
     Arrive
    2.54
    arrive
    2.50
     arrivals
    2.43
    arrived
    2.42
     Arrival
    2.41
    Activations Density 0.349%

    No Known Activations