© 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. 9618
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Has" and its variations or related forms

    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
     will
    -0.53
     has
    -0.50
     may
    -0.50
     have
    -0.47
     might
    -0.47
     can
    -0.46
     is
    -0.45
    存于互联网档案馆
    -0.45
     cannot
    -0.45
     should
    -0.44
    POSITIVE LOGITS
     Has
    1.29
    Has
    1.24
     Comes
    1.18
    Gives
    1.16
     Provides
    1.16
     Takes
    1.16
     Gives
    1.15
    Provides
    1.13
    Takes
    1.12
    Says
    1.11
    Activations Density 0.393%

    No Known Activations