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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 15248
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and symbols, likely focusing on syntactic structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    częściej
    -0.58
     Мексичка
    -0.51
    ='';
    
    -0.49
    ughty
    -0.49
    rijfs
    -0.48
    ứng
    -0.48
    iff
    -0.47
     Cof
    -0.47
    Fr
    -0.47
     chit
    -0.47
    POSITIVE LOGITS
    consulté
    0.86
    mybatisplus
    0.78
     AssemblyVersion
    0.77
    GeoNames
    0.71
     mangá
    0.70
    >(),
    0.69
     تضيفلها
    0.68
     consultato
    0.68
    }},\
    0.67
     Gorman
    0.66
    Activations Density 0.495%

    No Known Activations