© 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. 1-GEMMASCOPE-RES-16K
    11. 16110
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations related to organizations or technical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.73
    principalTable
    -0.69
    Diweddarwch
    -0.63
    namics
    -0.61
    XmlType
    -0.60
    AccessorTable
    -0.60
    IonicModule
    -0.59
    UpdateCommand
    -0.58
    enschappelijke
    -0.58
    uple
    -0.58
    POSITIVE LOGITS
    ac
    4.19
     ac
    2.98
     Ac
    2.91
    AC
    2.82
    Ac
    2.76
     AC
    2.26
     ACCOM
    1.95
    acs
    1.86
     Acc
    1.64
    Acc
    1.57
    Activations Density 0.071%

    No Known Activations