© 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. 5-GEMMASCOPE-RES-16K
    11. 6215
    Prev
    Next
    INDEX
    Explanations

    tokens that represent variables or parameters in mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     investi
    -0.78
     compri
    -0.74
     enthusi
    -0.74
     مرئيه
    -0.73
     expli
    -0.73
     esper
    -0.71
     equili
    -0.70
     iconFacebook
    -0.70
     exces
    -0.70
     opis
    -0.69
    POSITIVE LOGITS
    A
    1.31
    a
    1.24
    getA
    1.15
     A
    1.10
    aA
    1.05
     a
    0.96
    aData
    0.91
    bA
    0.90
     brancas
    0.87
     ansatte
    0.84
    Activations Density 0.336%

    No Known Activations