© 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 EvalsExportsAPI 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. 14452
    Prev
    Next
    INDEX
    Explanations

    references to ideology and political beliefs related to Zionism and its comparisons to other groups

    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
    MessageTagHelper
    -0.59
     ligiloj
    -0.56
    scribers
    -0.56
     känns
    -0.56
     AssemblyVersion
    -0.56
    InputTagHelper
    -0.55
    principalTable
    -0.54
     AttributeSet
    -0.53
    addPreferredGap
    -0.52
     koniecz
    -0.52
    POSITIVE LOGITS
    別に
    0.67
     clearly
    0.66
    Clearly
    0.62
    又不是
    0.62
     lawfully
    0.60
    確かに
    0.60
     Clearly
    0.59
     objectively
    0.59
     legitimately
    0.57
     legitimate
    0.57
    Activations Density 1.329%

    No Known Activations