© 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-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 10982
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical troubleshooting and querying processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "should" or its foreign equivalents

    np_acts-logits-general · gemini-2.0-flash

    advises or recommends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     приходится
    -0.46
    gsSP
    -0.45
    
    -0.43
     пришлось
    -0.39
    Portail
    -0.37
     diem
    -0.36
    hards
    -0.35
    DIPSETTING
    -0.34
    bA
    -0.34
    تقاوى
    -0.34
    POSITIVE LOGITS
     should
    2.23
    should
    2.02
     dovrebbe
    1.98
     debería
    1.96
    Should
    1.95
     Should
    1.91
     seharusnya
    1.90
     deberían
    1.90
     dovrebbero
    1.87
     devraient
    1.86
    Activations Density 0.941%

    No Known Activations