© 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. 13886
    Prev
    Next
    INDEX
    Explanations

    elements that signify unity and connection among individuals or groups

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

    concepts of unity, togetherness, and collective coming together.

    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
     vacate
    -0.33
     torpedo
    -0.32
    Šaltiniai
    -0.31
     gato
    -0.30
    clearpage
    -0.30
    伺
    -0.29
    Datuak
    -0.29
     stag
    -0.29
    hô
    -0.29
     acost
    -0.29
    POSITIVE LOGITS
     unity
    1.70
     uniting
    1.52
     united
    1.52
     unified
    1.48
     unifying
    1.46
     unite
    1.44
     cohesion
    1.42
     unify
    1.38
     cohesive
    1.38
     unites
    1.33
    Activations Density 0.408%

    No Known Activations