© 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. 17-GEMMASCOPE-RES-16K
    11. 7627
    Prev
    Next
    INDEX
    Explanations

    terms related to muscle regeneration and cancer treatment mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     détruit
    -0.57
     détruire
    -0.55
     coû
    -0.54
     vinto
    -0.53
    espé
    -0.53
     himſelf
    -0.52
     riuscito
    -0.52
    に出演
    -0.52
     licked
    -0.51
     Coordinating
    -0.51
    POSITIVE LOGITS
    への
    0.72
     creation
    0.70
     development
    0.67
     AssemblyCulture
    0.67
     management
    0.66
     formation
    0.64
    SceneManagement
    0.64
     acquisition
    0.64
     determination
    0.64
     manufacture
    0.63
    Activations Density 1.152%

    No Known Activations