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. 3-GEMMASCOPE-RES-16K
    6. 10221
    Prev
    Next
    INDEX
    Explanations

    conjunctions and terms that introduce clauses or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <<<<<<<<<<<<<<
    -0.87
    IntoConstraints
    -0.71
    queryInterface
    -0.70
    PerformLayout
    -0.66
     AssemblyCulture
    -0.64
    
    -0.61
    ArrowToggle
    -0.61
    TargetException
    -0.60
     Cuth
    -0.57
    {{/
    -0.57
    POSITIVE LOGITS
     dass
    1.30
     daß
    1.19
    ewel
    1.02
    Dass
    0.78
    dass
    0.76
     Obwohl
    0.73
     Wenn
    0.72
     weil
    0.70
     obwohl
    0.70
    enderror
    0.69
    Activations Density 0.111%

    No Known Activations