© 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. 39798
    Prev
    Next
    INDEX
    Explanations

    highly frequent occurrences of the "hl" token, indicating a potential focus on hyperlinks or references to high-level information

    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
    Wester
    -0.84
    Hozzáférés
    -0.80
     Daniels
    -0.78
    aurus
    -0.78
     Schenk
    -0.78
    aud
    -0.77
     Bundy
    -0.77
    +#+#
    -0.76
    WidgetItem
    -0.75
    Dud
    -0.75
    POSITIVE LOGITS
    hl
    1.29
     Ohl
    1.20
     HL
    1.07
     Ahl
    1.07
     hl
    1.05
    HL
    0.91
     Mühl
    0.90
    Hl
    0.89
     Mahl
    0.89
     chl
    0.88
    Activations Density 0.045%

    No Known Activations