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. 24-GEMMASCOPE-RES-16K
    6. 12521
    Prev
    Next
    INDEX
    Explanations

    terms related to government funding and taxation policies

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

    Prepositions and short words

    np_acts-logits-general · gemini-2.0-flash

    infrastructure and roads

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     financières
    -0.86
    
    -0.70
     financière
    -0.70
    TextHelper
    -0.67
    endphp
    -0.66
    jooq
    -0.60
    AccessorTable
    -0.59
    كويكب
    -0.58
    })));
    -0.58
     económica
    -0.57
    POSITIVE LOGITS
     infrastructure
    1.30
     infra
    1.02
    infrastructure
    0.99
     infrastructures
    0.94
     Infrastructure
    0.86
     roads
    0.86
    infra
    0.84
     infrastruktur
    0.77
    Infrastructure
    0.76
     social
    0.75
    Activations Density 0.200%

    No Known Activations