© 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. 3-GEMMASCOPE-RES-16K
    11. 2415
    Prev
    Next
    INDEX
    Explanations

    terms related to responses and reactions, particularly in a medical or therapeutic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ttino
    -0.59
    psis
    -0.58
    lebih
    -0.53
    UrlResolution
    -0.49
    ̈́
    -0.49
    ANCED
    -0.48
    enterOuterAlt
    -0.48
    DrawerToggle
    -0.48
     chi
    -0.48
     للمعارف
    -0.47
    POSITIVE LOGITS
     AssemblyProduct
    0.67
     Answering
    0.63
     Rued
    0.61
     sensibility
    0.59
    StringCopy
    0.59
     LCCN
    0.58
     sensitivities
    0.58
    UnknownFields
    0.57
     Addresses
    0.57
    VersionUID
    0.57
    Activations Density 0.377%

    No Known Activations