© 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. 7985
    Prev
    Next
    INDEX
    Explanations

    references to Nazi Germany and its historical actions

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

    historical references to Nazi Germany and related World War II events.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    references to Nazi Germany and related World War II historical context.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    mentions of Nazi Germany and World War II–era fascist entities, leaders, events, and policies.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    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
    delwed
    -0.50
     Mühle
    -0.44
     Endlich
    -0.43
     Transparen
    -0.40
     Baumwolle
    -0.40
     Orgel
    -0.39
     Leuven
    -0.39
    pă
    -0.38
    zessin
    -0.38
     viață
    -0.38
    POSITIVE LOGITS
     Hitler
    1.15
    Hitler
    1.08
     Nazi
    1.02
    Nazi
    0.85
     fascist
    0.85
     nazi
    0.82
     Nazis
    0.82
     Adolf
    0.75
     Aryan
    0.73
     Hit
    0.69
    Activations Density 0.266%

    No Known Activations