© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 16082
    Prev
    Next
    INDEX
    Explanations

    references to significant geographical or notable entities, particularly using the terms "Great" and "Big."

    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
    PerformLayout
    -1.04
     שוליים
    -0.97
     disambiguazione
    -0.97
     resourceCulture
    -0.90
     snippetHide
    -0.89
    nvarchar
    -0.87
     propOrder
    -0.86
     <<<<<<<<<<<<<<
    -0.84
    ResumeLayout
    -0.82
    ViewFeatures
    -0.82
    POSITIVE LOGITS
    Ch
    0.62
    field
    0.61
    Alpha
    0.60
    St
    0.56
    Field
    0.56
     attempted
    0.56
     respectivos
    0.56
    alpha
    0.56
    san
    0.55
    Black
    0.51
    Activations Density 0.042%

    No Known Activations