© 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. 2233
    Prev
    Next
    INDEX
    Explanations

    phrases that express disagreement or critique of actions and policies

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

    negative consequences or harmful outcomes described through comparative or causal language.

    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
    suddenly
    -0.44
     repente
    -0.38
     sudden
    -0.38
     dared
    -0.38
    omin
    -0.38
     geme
    -0.36
     suddenly
    -0.36
     Sudden
    -0.35
    wiki
    -0.35
    이터
    -0.35
    POSITIVE LOGITS
     detriment
    0.83
     unnecessarily
    0.77
     harmful
    0.77
     detrimental
    0.77
     harms
    0.76
     harm
    0.74
     pointless
    0.73
     inuti
    0.73
     merusak
    0.72
     inneces
    0.72
    Activations Density 0.785%

    No Known Activations