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

    Neuronpedia

    Jacobian LensNEW
    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. 5392
    Prev
    Next
    INDEX
    Explanations

    references to studies and research findings

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

    the word "studies" and related academic research terminology.

    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
    expandindo
    -0.65
    Hentet
    -0.55
    лтемелер
    -0.52
     AssemblyVersion
    -0.52
    enterOuterAlt
    -0.52
    ScopeManager
    -0.51
     Chwiliwch
    -0.51
     мәкал
    -0.48
    sizeCache
    -0.48
    queryInterface
    -0.48
    POSITIVE LOGITS
     indicates
    1.64
     shows
    1.63
     suggests
    1.59
     indicate
    1.46
     reveals
    1.40
     suggest
    1.39
    shows
    1.34
    indicates
    1.34
     showed
    1.28
     show
    1.19
    Activations Density 1.228%

    No Known Activations