© 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. 31-GEMMASCOPE-RES-16K
    11. 9636
    Prev
    Next
    INDEX
    Explanations

    references to organizations, authorities, or entities involved in statistics or data manipulation

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

    proper names and titles of specific individuals, organizations, and places.

    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
     BIBSYS
    -0.55
    Становништво
    -0.46
     informée
    -0.46
     esternos
    -0.43
    cửa
    -0.43
     fillers
    -0.43
     filler
    -0.42
    Glej
    -0.42
     שוליים
    -0.42
     Filler
    -0.42
    POSITIVE LOGITS
    setVerticalGroup
    0.75
    Personendaten
    0.68
    CloseOperation
    0.54
    webElementXpaths
    0.51
    posedge
    0.50
    SourceChecksum
    0.49
     AssemblyVersion
    0.46
     تعدى
    0.44
    ArrowToggle
    0.43
     actionMode
    0.43
    Activations Density 16.593%

    No Known Activations