© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 11349
    Prev
    Next
    INDEX
    Explanations

    references to economic impacts and affected groups or entities in various situations

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

    negative consequences or adverse effects on people, places, or situations.

    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
     lazy
    -0.32
    ü
    -0.28
    Lazy
    -0.27
    ul
    -0.27
    laub
    -0.27
     Lazy
    -0.27
     кло
    -0.27
     AP
    -0.26
     WANTED
    -0.25
     DIY
    -0.25
    POSITIVE LOGITS
     affected
    2.52
     impacted
    2.28
     Affected
    2.25
    affected
    2.16
    Affected
    2.09
     impact
    1.81
     AFFECT
    1.77
     afectados
    1.74
     afectado
    1.73
     impacts
    1.71
    Activations Density 0.578%

    No Known Activations