© 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. 34-GEMMASCOPE-RES-16K
    11. 8970
    Prev
    Next
    INDEX
    Explanations

    connections between political actions and ethical principles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defStyleAttr
    -0.45
    ValueStyle
    -0.45
     pygame
    -0.43
     welcher
    -0.43
    chartInstance
    -0.42
     тях
    -0.39
     ایشان
    -0.39
    okości
    -0.38
    rawDesc
    -0.37
    ersonal
    -0.37
    POSITIVE LOGITS
     its
    3.36
    Its
    2.69
     Its
    2.59
    它的
    2.27
    its
    2.13
     itself
    2.11
     Оно
    2.03
     оно
    1.89
     Itself
    1.72
    itself
    1.69
    Activations Density 2.454%

    No Known Activations