© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 39709
    Prev
    Next
    INDEX
    Explanations

    terms related to controversy or contentious issues

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     Hagen
    -0.68
     sĩ
    -0.61
     naturels
    -0.60
     diinginkan
    -0.58
    >=</
    -0.58
     kepad
    -0.57
    mädchen
    -0.57
    يئة
    -0.57
    bekah
    -0.56
    ridae
    -0.56
    POSITIVE LOGITS
    versial
    1.36
     controversy
    1.32
     controversies
    1.23
     Controversy
    1.17
     controver
    1.16
     controversial
    1.14
     controversi
    1.09
    Controversy
    1.08
     Contro
    1.02
     contro
    0.91
    Activations Density 0.011%

    No Known Activations