© 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. 7-GEMMASCOPE-RES-16K
    11. 7471
    Prev
    Next
    INDEX
    Explanations

    instances of hypocrisy or contradictory behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     समीक्षाओं
    -0.55
     &___
    -0.43
    SuccessListener
    -0.43
    Meto
    -0.42
     løs
    -0.40
    URIComponent
    -0.40
    Примітки
    -0.40
     Gemein
    -0.40
     gebru
    -0.40
     didReceive
    -0.40
    POSITIVE LOGITS
     hypocrite
    0.84
     hypocritical
    0.80
     hypocrisy
    0.76
    crites
    0.71
     defaultstate
    0.71
    Hypo
    0.70
    crisy
    0.69
    adox
    0.68
     ddelweddau
    0.68
    WithMany
    0.68
    Activations Density 0.298%

    No Known Activations