© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 532
    Prev
    Next
    INDEX
    Explanations

    negations and qualifiers indicating uncertainty or exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.39
    }*/
    -0.33
     Pembangunan
    -0.32
    })*/
    -0.32
    otherwise
    -0.32
     finalement
    -0.31
     otherwise
    -0.31
     Lingkungan
    -0.31
    queryInterface
    -0.31
    whatever
    -0.30
    POSITIVE LOGITS
     reason
    0.86
     dearth
    0.77
     danger
    0.73
     shortage
    0.73
     possibility
    0.73
     tendency
    0.71
     inherent
    0.67
    possibility
    0.67
     discrepancy
    0.67
     difference
    0.67
    Activations Density 0.325%

    No Known Activations