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

    Neuronpedia

    Jacobian LensNEW
    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. 2-GEMMASCOPE-RES-16K
    11. 3371
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "has" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purpoſe
    -0.67
     houſe
    -0.65
     fubject
    -0.63
     ſtate
    -0.61
     preſent
    -0.59
     uſe
    -0.59
    ſelves
    -0.58
    PerformLayout
    -0.58
     themſelves
    -0.57
     ſche
    -0.56
    POSITIVE LOGITS
     has
    2.34
     έχει
    1.20
     is
    1.19
    has
    1.16
     Has
    1.13
     heeft
    1.09
    Has
    1.04
     має
    1.04
     HAS
    1.03
     имеет
    0.94
    Activations Density 0.123%

    No Known Activations