© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 3385
    Prev
    Next
    INDEX
    Explanations

    phrases related to exploitation and moral issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    harmful malicious actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.63
     modalités
    -0.55
     سكانية
    -0.53
     ekst
    -0.52
    šanai
    -0.51
    مزید
    -0.48
    StringUtil
    -0.48
    titud
    -0.47
    іга
    -0.47
    =$?
    -0.47
    POSITIVE LOGITS
     innocent
    1.42
     harmless
    1.14
    innocent
    1.11
     innoc
    1.07
     inocente
    1.05
     legitimate
    1.01
     Innocent
    0.99
     innocently
    0.98
    好不容易
    0.93
     defen
    0.89
    Activations Density 0.331%

    No Known Activations