© 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-2-2B
    7. Residual Stream - 16k
    9. 6-GEMMASCOPE-RES-16K
    11. 1122
    Prev
    Next
    INDEX
    Explanations

    the word "Having" and variations of it, indicating a focus on phrases that express possession or the completion of an action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/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.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    شف
    -0.56
     zwycię
    -0.54
    strconv
    -0.54
    <b>
    -0.53
     scuro
    -0.52
     brillante
    -0.52
     Esch
    -0.51
    Pipeline
    -0.51
     Wils
    -0.51
    Phương
    -0.50
    POSITIVE LOGITS
     having
    1.28
    rungsseite
    1.26
    having
    1.22
     HAVING
    1.16
     Having
    1.15
    Having
    1.10
     BEING
    1.04
     being
    1.01
    being
    0.98
     Being
    0.96
    Activations Density 0.084%

    No Known Activations