© 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. 14-GEMMASCOPE-RES-16K
    11. 4378
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal norms and integrity in professional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.88
     AssemblyCulture
    -0.85
     himo
    -0.76
    addCriterion
    -0.73
    出版年
    -0.73
    ]--;
    -0.72
     Савезне
    -0.71
    protoimpl
    -0.69
    CodedInputStream
    -0.68
     getchar
    -0.66
    POSITIVE LOGITS
    Maintaining
    0.73
     Maintaining
    0.70
     maintaining
    0.66
     maintain
    0.65
     preserving
    0.63
     mempertahankan
    0.62
     Maintain
    0.60
     preserve
    0.60
     manter
    0.60
     preserved
    0.58
    Activations Density 0.405%

    No Known Activations