© 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 - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 7766
    Prev
    Next
    INDEX
    Explanations

    references to a specific concept or entity denoted by the term 'cre'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    لينكات
    -0.78
    DOCTYPE
    -0.72
     ब्रेकडाउन
    -0.70
    NewUrlParser
    -0.69
    VolleyError
    -0.65
     Larissa
    -0.64
     Shopee
    -0.63
    MigrationBuilder
    -0.63
    utnik
    -0.62
    ActivityCompat
    -0.61
    POSITIVE LOGITS
     cre
    1.50
    Cre
    1.42
    cre
    1.34
     Cre
    1.32
     CRE
    1.24
    CRE
    1.08
     Creation
    0.91
    creation
    0.89
     Cré
    0.88
    Creation
    0.88
    Activations Density 0.072%

    No Known Activations