© 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-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 6200
    Prev
    Next
    INDEX
    Explanations

    formal language related to acknowledgments and collaborations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.95
    AccessorTable
    -0.92
    WebVitals
    -0.83
    principalColumn
    -0.82
     kasarigan
    -0.80
     propOrder
    -0.74
    tagHelperRunner
    -0.73
    Tikang
    -0.73
     EconPapers
    -0.72
     isInitialized
    -0.71
    POSITIVE LOGITS
     soltanto
    0.67
     mustn
    0.64
     programmes
    0.59
     Asimismo
    0.58
     programme
    0.58
     toutefois
    0.57
    Alongside
    0.55
    favourable
    0.53
     gradually
    0.53
     precisely
    0.51
    Activations Density 1.070%

    No Known Activations