© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 13155
    Prev
    Next
    INDEX
    Explanations

    instances of the word "wrong" and related concepts of wrongdoing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſhe
    -0.63
     houſe
    -0.57
    awsze
    -0.56
     ſtate
    -0.56
    disfraz
    -0.53
     niyang
    -0.52
     Armour
    -0.51
     puntata
    -0.51
     perſon
    -0.51
    bicara
    -0.50
    POSITIVE LOGITS
     pregnant
    1.14
     wrong
    1.07
     Pregnant
    1.04
    pregnant
    0.98
     pregnancy
    0.98
    Pregnancy
    0.91
    MigrationBuilder
    0.88
     reproduction
    0.87
     Reproduction
    0.85
    wrong
    0.85
    Activations Density 0.075%

    No Known Activations