© 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-2-2B
    7. Residual Stream - 16k
    9. 13-GEMMASCOPE-RES-16K
    11. 10454
    Prev
    Next
    INDEX
    Explanations

    references to political ideologies and socio-political promises within narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ardes
    -0.59
     né
    -0.51
    anal
    -0.46
     affects
    -0.45
    場合があります
    -0.43
     y
    -0.42
    тена
    -0.42
    のですか
    -0.42
     Mary
    -0.41
    estre
    -0.41
    POSITIVE LOGITS
    Hochspringen
    0.78
    SequentialGroup
    0.77
     myſelf
    0.73
     pleaſure
    0.72
     hoped
    0.71
     Theſe
    0.69
     $_"
    0.69
     Biôgrafia
    0.68
     raiſ
    0.67
     ſever
    0.65
    Activations Density 0.408%

    No Known Activations