© 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. 14012
    Prev
    Next
    INDEX
    Explanations

    references to personal relationships and emotional connections

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

    references to the pronoun "me" or personal experiences involving the speaker.

    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
     дописавши
    -0.39
    zierte
    -0.38
    nEnter
    -0.36
    */].
    -0.34
     Fas
    -0.34
    ecuted
    -0.33
     приш
    -0.33
     แม
    -0.33
     Процитовано
    -0.33
     chic
    -0.33
    POSITIVE LOGITS
    tagHelperRunner
    0.75
    DockStyle
    0.68
    tangentMode
    0.62
     personally
    0.62
     ModelExpression
    0.57
     personalmente
    0.56
     CreateTagHelper
    0.55
     persönlich
    0.54
    zelf
    0.50
    enderror
    0.50
    Activations Density 0.248%

    No Known Activations