© 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. 7950
    Prev
    Next
    INDEX
    Explanations

    discussions surrounding political themes and debates

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

    references to political discourse and partisan debate.

    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
    hadiran
    -0.44
     Milán
    -0.37
     Occidente
    -0.36
     setempat
    -0.36
     technischen
    -0.35
     الشركة
    -0.35
    Hinweise
    -0.35
     pener
    -0.34
     kwiet
    -0.34
     szpital
    -0.34
    POSITIVE LOGITS
     political
    2.36
     politics
    2.09
    political
    2.05
     Political
    2.02
    Political
    1.98
     politicians
    1.89
     politician
    1.84
     POLITICAL
    1.84
     politically
    1.80
     Politics
    1.80
    Activations Density 1.415%

    No Known Activations