© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 16241
    Prev
    Next
    INDEX
    Explanations

    elements and features related to absorbent materials and their construction in products like diapers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Theſe
    -1.01
    ModelAdmin
    -1.01
     Efq
    -0.98
     ―――――
    -0.97
     myſelf
    -0.96
    bootstrapcdn
    -0.92
     GenerationType
    -0.91
     pleaſure
    -0.88
    SpringBootTest
    -0.87
    HomeAsUpEnabled
    -0.87
    POSITIVE LOGITS
     inside
    0.52
     inner
    0.47
    liner
    0.46
     interior
    0.46
    intérieur
    0.45
    内
    0.44
     liner
    0.42
     contre
    0.41
     内
    0.39
     Inside
    0.39
    Activations Density 0.335%

    No Known Activations