© 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. 40-GEMMASCOPE-RES-16K
    11. 5626
    Prev
    Next
    INDEX
    Explanations

    references to accessibility and inclusivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    calientes
    -0.48
     Yerevan
    -0.48
     Lusaka
    -0.47
     HasFactory
    -0.46
    MockMvc
    -0.44
     Chengdu
    -0.44
    amqp
    -0.42
     Budapest
    -0.42
     Bergamo
    -0.41
     Phry
    -0.41
    POSITIVE LOGITS
     beach
    2.19
     coastal
    2.17
     seaside
    2.14
     ocean
    2.13
     seashore
    2.11
     sea
    2.05
     seawater
    1.99
     beachfront
    1.99
     Beach
    1.94
    Beach
    1.92
    Activations Density 0.967%

    No Known Activations