© 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. 4983
    Prev
    Next
    INDEX
    Explanations

    references to geographical features or locations, specifically those with the term "ridge."

    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
     للمعارف
    -0.82
    WebMethod
    -0.81
    }*/
    -0.79
     autorytatywna
    -0.79
     Belf
    -0.78
    \!
    -0.77
    .~(\
    -0.74
    プロン
    -0.74
    *************
    -0.74
    __*/
    -0.73
    POSITIVE LOGITS
     Ridge
    1.91
    Ridge
    1.83
     ridge
    1.77
     RIDGE
    1.68
     ridges
    1.55
     Rid
    1.44
    Rid
    1.37
    ridge
    1.33
     rid
    1.15
     RID
    1.11
    Activations Density 0.009%

    No Known Activations