© 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. 11-GEMMASCOPE-RES-16K
    11. 8482
    Prev
    Next
    INDEX
    Explanations

    references to concepts of moral dilemmas and ethical considerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.84
    RegressionTest
    -0.72
    AxisAlignment
    -0.71
     initComponents
    -0.70
    Odkazy
    -0.69
     يتيمه
    -0.68
    曖昧さ回避
    -0.67
     NUKAT
    -0.66
    Referințe
    -0.65
     tartalomajánló
    -0.64
    POSITIVE LOGITS
    abstractmethod
    0.48
     sur
    0.42
    textTheme
    0.41
    urlpatterns
    0.41
    UnknownFields
    0.40
    moduleId
    0.40
    domo
    0.40
    naeus
    0.37
     ge
    0.37
    wati
    0.37
    Activations Density 1.476%

    No Known Activations