© 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. 7357
    Prev
    Next
    INDEX
    Explanations

    references to poetry and the act of mapping

    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
     otomatig
    -0.67
     Administrativna
    -0.66
    ViewFeatures
    -0.63
     ComVisible
    -0.61
     AssemblyCulture
    -0.60
     löyty
    -0.58
    MessageTagHelper
    -0.58
     aikaa
    -0.57
     väli
    -0.56
     indígen
    -0.54
    POSITIVE LOGITS
     logic
    0.64
     Ul
    0.60
     Logic
    0.57
     ult
    0.57
     Topology
    0.55
     topology
    0.54
     Topo
    0.54
     ul
    0.54
     Honors
    0.54
     Poetry
    0.53
    Activations Density 0.251%

    No Known Activations