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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6108
    Prev
    Next
    INDEX
    Explanations

    expressions of physical and emotional sensations

    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
     moderation
    -0.68
    IUrlHelper
    -0.66
     deafness
    -0.60
     blindness
    -0.60
    +:+
    -0.55
     bacio
    -0.55
     Sünde
    -0.54
     Moder
    -0.54
     screams
    -0.53
     moder
    -0.53
    POSITIVE LOGITS
     stressed
    1.00
     agitated
    0.99
     upset
    0.98
     distressed
    0.83
    stressed
    0.82
     depressed
    0.80
     perturbed
    0.77
     distraught
    0.70
     disturbed
    0.70
     tense
    0.69
    Activations Density 0.189%

    No Known Activations