© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 7586
    Prev
    Next
    INDEX
    Explanations

    phrases related to practical applications or implementations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    новништво
    -0.52
     setLoading
    -0.49
     CreateTagHelper
    -0.48
     Italijani
    -0.48
    IndentedString
    -0.44
    -------------</
    -0.42
     ModelExpression
    -0.42
    tagHelperRunner
    -0.42
    路由
    -0.42
     appContext
    -0.41
    POSITIVE LOGITS
    Observer
    0.68
    observer
    0.66
     practical
    0.66
    Practical
    0.66
     Practical
    0.65
     Observer
    0.58
    dian
    0.57
     observer
    0.56
     apparent
    0.56
     specimen
    0.53
    Activations Density 0.198%

    No Known Activations