© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4748
    Prev
    Next
    INDEX
    Explanations

    names and titles related to people and their achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    featureID
    -0.69
     typelib
    -0.61
     ProtoMessage
    -0.61
    CppMethod
    -0.60
    HideFlags
    -0.60
    ValueStyle
    -0.60
    XmlAccessorType
    -0.57
    ⤹
    -0.56
    OfWork
    -0.55
    =?";
    -0.55
    POSITIVE LOGITS
    ha
    0.94
    wa
    0.91
    HA
    0.75
     Wa
    0.71
    ya
    0.71
    Wa
    0.70
    WA
    0.66
    Ha
    0.62
     Ha
    0.61
    za
    0.57
    Activations Density 2.155%

    No Known Activations