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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 8238
    Prev
    Next
    INDEX
    Explanations

    references to conservative political ideologies and their implications in governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rain
    -0.43
     RAIN
    -0.43
     Rain
    -0.42
    Rain
    -0.40
    rain
    -0.37
    雨
    -0.37
     rains
    -0.36
     wet
    -0.34
     enfer
    -0.34
     hydro
    -0.34
    POSITIVE LOGITS
    AntiForgeryToken
    0.78
     Conservative
    0.71
     Conservatives
    0.69
     conservatives
    0.68
     conservative
    0.68
    Conservative
    0.68
    anyahu
    0.65
     conservatism
    0.63
     GOP
    0.63
     Republican
    0.62
    Activations Density 1.236%

    No Known Activations