© 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. 5055
    Prev
    Next
    INDEX
    Explanations

    quantitative data and financial terms related to school district funding and budgeting

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

    financial and policy-related numeric values and statistics.

    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
     hoek
    -0.37
     podjela
    -0.36
     Wikiseite
    -0.35
     Behör
    -0.34
     assuré
    -0.34
     estrenar
    -0.34
     anunciar
    -0.34
    Formazione
    -0.33
     incele
    -0.33
     praktik
    -0.33
    POSITIVE LOGITS
     referendum
    1.50
     ballot
    1.37
     voters
    1.30
     Voters
    1.23
     voter
    1.15
     plebis
    1.13
     Ballot
    1.11
     vote
    1.09
     Refer
    1.05
     refer
    1.02
    Activations Density 0.234%

    No Known Activations