© 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 - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 9018
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to initialization or beginnings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    er
    -0.83
    jö
    -0.67
     LCCN
    -0.60
     it
    -0.60
    führ
    -0.59
     tovább
    -0.59
    робнее
    -0.58
     simply
    -0.58
    ついて
    -0.57
     doubt
    -0.57
    POSITIVE LOGITS
     getStart
    1.03
    getStart
    0.93
    تقاوى
    0.87
     OPENING
    0.83
     Opening
    0.82
     Greet
    0.82
    ंदीखरीदारी
    0.82
     Soledad
    0.79
    StoryboardSegue
    0.78
     الحره
    0.77
    Activations Density 0.102%

    No Known Activations