Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 56817
    Prev
    Next
    INDEX
    Explanations

    references to health-related conditions or disorders

    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
     estekak
    -0.91
    GOTREF
    -0.87
     ▼
    -0.80
     חיצוניים
    -0.77
     Whal
    -0.76
    GEBURTSDATUM
    -0.76
     bå
    -0.75
    спеди
    -0.74
    VERTIS
    -0.73
    RetentionPolicy
    -0.73
    POSITIVE LOGITS
     Ill
    1.28
    Ill
    1.24
     ILL
    1.16
     ill
    1.14
     Illness
    1.05
     Illy
    0.97
     illness
    0.96
     Sill
    0.96
    lll
    0.93
     illnesses
    0.91
    Activations Density 0.025%

    No Known Activations