© 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. 35-GEMMASCOPE-RES-16K
    11. 7496
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and relationships related to sets 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 @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.62
     يتيمه
    -0.50
     gynhyrchwyd
    -0.49
    CodeAttribute
    -0.45
    TemporalType
    -0.42
    <?
    -0.41
     informée
    -0.40
     ddelweddau
    -0.40
    ⤹
    -0.38
    
    -0.38
    POSITIVE LOGITS
     intersection
    1.53
     union
    1.45
    intersection
    1.31
     Intersection
    1.30
     intersect
    1.27
     intersections
    1.25
    union
    1.23
    Intersection
    1.22
     Union
    1.17
    Union
    1.13
    Activations Density 1.214%

    No Known Activations