© 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. 1543
    Prev
    Next
    INDEX
    Explanations

    references to military themes and terminology

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

    words and phrases related to aggression, conflict, and confrontational 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
    UnusedPrivate
    -0.42
    îtra
    -0.37
     jätte
    -0.37
     Riesen
    -0.36
     wyś
    -0.36
     estad
    -0.36
     maravillosa
    -0.35
     additionally
    -0.35
     encantador
    -0.35
     tolle
    -0.35
    POSITIVE LOGITS
     fuckin
    0.92
     motherfucker
    0.88
     homie
    0.87
     fucked
    0.79
     hella
    0.76
     bitches
    0.75
     niggas
    0.75
     fucking
    0.74
     fuck
    0.74
     shit
    0.74
    Activations Density 0.276%

    No Known Activations