© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 5305
    Prev
    Next
    INDEX
    Explanations

    references to organizational capabilities and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     entanto
    -0.56
     étoit
    -0.55
     Want
    -0.53
     vouloir
    -0.53
    ();)
    -0.53
     ganas
    -0.53
     want
    -0.52
     pamamagitan
    -0.50
    Want
    -0.50
     need
    -0.48
    POSITIVE LOGITS
     easily
    1.38
    easily
    1.15
     comfortably
    1.08
     Easily
    1.07
     efficiently
    1.03
     readily
    1.02
    Easily
    1.02
     freely
    1.02
     safely
    1.01
     confidently
    1.01
    Activations Density 0.286%

    No Known Activations