© 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. 8044
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to responsibility

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

    phrases describing catastrophic or world-ending scenarios.

    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
    httphttps
    -0.71
     kasarigan
    -0.65
     Wicidata
    -0.65
     ModelExpression
    -0.64
     propOrder
    -0.61
    Rüyada
    -0.57
    
    -0.53
    もしれない
    -0.53
    RenderAtEndOf
    -0.52
    脚注の使い方
    -0.52
    POSITIVE LOGITS
     as
    1.61
     كما
    1.28
     както
    1.13
    正如
    1.12
     sebagaimana
    1.07
     как
    1.03
     zoals
    0.96
     như
    0.95
     όπως
    0.92
     як
    0.88
    Activations Density 1.466%

    No Known Activations