© 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. 3-GEMMASCOPE-RES-16K
    11. 13724
    Prev
    Next
    INDEX
    Explanations

    information related to living locations and personal background

    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
     quality
    -0.45
     ok
    -0.43
    PointSize
    -0.42
    Traversal
    -0.42
    ceta
    -0.41
     ویکی‌پدی
    -0.41
    biam
    -0.41
    +(-
    -0.41
    ICE
    -0.40
    té
    -0.40
    POSITIVE LOGITS
     resourceCulture
    0.85
     ddelweddau
    0.79
    esModule
    0.77
    xymatrix
    0.74
     vivimos
    0.71
     BorderRadius
    0.70
    Affiliation
    0.70
    parsedMessage
    0.68
    
    0.68
    UnusedPrivate
    0.67
    Activations Density 0.256%

    No Known Activations