© 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. 7090
    Prev
    Next
    INDEX
    Explanations

    mentions of educational institutions and related transitions

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

    proper nouns and geographic locations, particularly city names and organizational titles.

    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
    richTextPanel
    -0.50
    ConstraintMaker
    -0.50
     AssemblyProduct
    -0.48
    httphttps
    -0.47
     knex
    -0.43
    sidemargin
    -0.43
     OFDb
    -0.42
    +#+#
    -0.42
     disambiguazione
    -0.40
     ligiloj
    -0.40
    POSITIVE LOGITS
     Los
    1.25
     LA
    1.11
    Los
    1.09
     UCLA
    0.94
     Pasadena
    0.87
    LA
    0.85
     Angeles
    0.84
     LAP
    0.84
     Hollywood
    0.84
     LAX
    0.82
    Activations Density 0.238%

    No Known Activations