© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11316
    Prev
    Next
    INDEX
    Explanations

    concepts related to programming logic and data structures, particularly arrays and their operations

    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
    DockStyle
    -0.40
    InjectAttribute
    -0.35
     drzwi
    -0.35
    лтамалар
    -0.35
    ]=='
    -0.33
     ListTile
    -0.32
     HttpNotFound
    -0.31
    ± 
    -0.30
     Stork
    -0.29
    SpringBootTest
    -0.29
    POSITIVE LOGITS
     array
    2.33
     Array
    2.13
     arrays
    2.03
    array
    1.97
    Array
    1.93
     ARRAY
    1.85
    数组
    1.83
     Arrays
    1.73
    ARRAY
    1.70
    arrays
    1.54
    Activations Density 0.787%

    No Known Activations