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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 13498
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical achievements and significant milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    verb phrases indicating achievement, succession, or attainment of positions and milestones.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rüyada
    -0.75
    numerusform
    -0.73
    ngdoc
    -0.68
     nakalista
    -0.66
     autorytatywna
    -0.65
    PyExc
    -0.63
    fromnode
    -0.63
     lenker
    -0.63
    LookAnd
    -0.61
     transfieras
    -0.60
    POSITIVE LOGITS
     Britain
    0.62
     America
    0.61
     our
    0.60
    Britain
    0.47
    America
    0.44
     Indias
    0.44
     Deutschlands
    0.40
     Italy
    0.38
     america
    0.37
     India
    0.36
    Activations Density 0.564%

    No Known Activations