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. 15-GEMMASCOPE-RES-16K
    6. 8978
    Prev
    Next
    INDEX
    Explanations

    monetary values and prices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.88
    }")]
    -0.80
    MENAFN
    -0.79
    GEBURTSDATUM
    -0.79
    PerformLayout
    -0.77
    SourceChecksum
    -0.76
     EconPapers
    -0.71
    Véxase
    -0.70
    .}}
    -0.70
     AssemblyTitle
    -0.70
    POSITIVE LOGITS
    -$
    0.66
     cash
    0.62
     dollars
    0.56
     million
    0.56
     spent
    0.54
     trị
    0.53
     billion
    0.52
     worth
    0.52
     trillion
    0.52
    0
    0.50
    Activations Density 0.257%

    No Known Activations