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. 9117
    Prev
    Next
    INDEX
    Explanations

    references to properties and props in programming contexts, particularly regarding their usage and behavior in code

    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
    ValueStyle
    -1.17
    发表于
    -0.90
     bisog
    -0.88
    SourceChecksum
    -0.86
    urfacing
    -0.84
    //</
    -0.84
     Eller
    -0.82
     tė
    -0.80
     justices
    -0.80
     preliminar
    -0.80
    POSITIVE LOGITS
    props
    1.98
     props
    1.91
     Props
    1.75
    Props
    1.68
     prop
    1.49
     Prop
    1.36
    PROPS
    1.29
    prop
    1.25
    Prop
    1.23
     PROP
    1.13
    Activations Density 0.052%

    No Known Activations