© 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. 16-GEMMASCOPE-RES-16K
    11. 13090
    Prev
    Next
    INDEX
    Explanations

    expressions of progress or ongoing actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ั่น
    -0.37
     mesin
    -0.37
    ">//
    -0.34
     pédagog
    -0.32
     due
    -0.31
     одновременно
    -0.30
     fondament
    -0.29
     oubli
    -0.28
     when
    -0.28
     debido
    -0.28
    POSITIVE LOGITS
     bisher
    0.87
     bisherigen
    0.82
     bislang
    0.80
     sejauh
    0.77
    fjspx
    0.73
    featureID
    0.71
     heretofore
    0.65
    Gambas
    0.64
     hitherto
    0.64
    setVerticalGroup
    0.63
    Activations Density 0.108%

    No Known Activations