© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 7648
    Prev
    Next
    INDEX
    Explanations

    references to political leaders and their actions or policies

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

    conservative viewpoints and right-leaning politics

    np_acts-logits-general · gemini-2.0-flash

    far-right Heritage Foundation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Quaker
    -0.35
     gap
    -0.34
    lauf
    -0.34
     EQU
    -0.34
    itets
    -0.34
     kli
    -0.34
     learning
    -0.33
     rain
    -0.32
     images
    -0.32
     Geme
    -0.32
    POSITIVE LOGITS
     conservatives
    0.97
     conservative
    0.88
    Conserv
    0.84
     Conservatives
    0.82
    conservative
    0.81
     conservatism
    0.79
    conserv
    0.77
     Conservative
    0.75
     konserv
    0.74
    Conservative
    0.73
    Activations Density 0.531%

    No Known Activations