© 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. 15286
    Prev
    Next
    INDEX
    Explanations

    instances and references to ice and ice-based items

    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
     propOrder
    -1.17
    BibitemShut
    -0.95
    theless
    -0.94
    chyma
    -0.91
    NamedQueries
    -0.90
    Demografía
    -0.88
     bezeichneter
    -0.87
    erunner
    -0.85
    urably
    -0.85
    __*/
    -0.84
    POSITIVE LOGITS
     Ice
    1.41
     ice
    1.40
     ICE
    1.39
    Ice
    1.34
    ICE
    0.96
    ice
    0.94
     Eis
    0.94
     iced
    0.88
    eis
    0.87
     hielo
    0.78
    Activations Density 0.008%

    No Known Activations