© 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 - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 24964
    Prev
    Next
    INDEX
    Explanations

    elements related to contrasting concepts or entities within a specific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Autoritní
    -0.82
    脚注の使い方
    -0.60
    #+#
    -0.59
     ***!
    -0.58
    зулта
    -0.56
     disambiguazione
    -0.54
    CrossRef
    -0.54
    ябре
    -0.51
    солю
    -0.51
    цездатний
    -0.50
    POSITIVE LOGITS
     henvisninger
    0.69
     alike
    0.60
    moiselle
    0.60
    haustible
    0.58
    [...,
    0.56
     testSet
    0.54
    DispatchToProps
    0.52
    plein
    0.51
    rokken
    0.49
    ρης
    0.49
    Activations Density 0.186%

    No Known Activations