© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 7251
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "have."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Comes before "have" or "had"

    np_acts-logits-general · gemini-2.0-flash

    having or possessing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jsdelivr
    -0.46
     étapes
    -0.40
    Svara
    -0.38
     szóci
    -0.38
    Хьажоргаш
    -0.36
     plufieurs
    -0.35
    newList
    -0.34
     farlo
    -0.34
     ſtate
    -0.34
     frattempo
    -0.34
    POSITIVE LOGITS
     Memiliki
    0.80
     mempunyai
    0.79
     memiliki
    0.79
     punya
    0.77
     posiada
    0.75
    有过
    0.71
     иметь
    0.71
    unyai
    0.71
    have
    0.70
     have
    0.70
    Activations Density 0.662%

    No Known Activations