© 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-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 2597
    Prev
    Next
    INDEX
    Explanations

    technical terms related to materials and their properties in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.60
     händer
    -0.51
    elemField
    -0.50
    脚注の使い方
    -0.50
     nameof
    -0.49
    mogorov
    -0.49
     καν
    -0.49
    AccessorTable
    -0.49
    UnsafeEnabled
    -0.48
    Personendaten
    -0.48
    POSITIVE LOGITS
     act
    2.46
     acting
    2.31
     acted
    2.27
     acts
    2.27
     serve
    2.05
    act
    1.99
     serves
    1.95
     Act
    1.94
    Act
    1.90
     Acting
    1.86
    Activations Density 0.857%

    No Known Activations