© 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. 5-GEMMASCOPE-RES-16K
    11. 993
    Prev
    Next
    INDEX
    Explanations

    identifiers, particularly variables and function names in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.54
     don
    -0.50
     
    -0.45
    DON
    -0.42
     im
    -0.40
    ");
    -0.39
     Fin
    -0.39
    ↵↵
    -0.38
    );
    -0.38
     mídia
    -0.38
    POSITIVE LOGITS
     Efq
    1.05
     purpoſe
    1.02
     Monfieur
    0.99
     ſtate
    0.97
     houſe
    0.96
     ſta
    0.92
     pleaſure
    0.92
     greateſt
    0.91
     Reſ
    0.90
     Majefty
    0.90
    Activations Density 0.064%

    No Known Activations