© 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
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 15239
    Prev
    Next
    INDEX
    Explanations

    the word "of" in various contexts throughout the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flüssigkeit
    -0.58
    seamnă
    -0.58
     lisäksi
    -0.53
     megjelen
    -0.53
     anún
    -0.53
    guiente
    -0.53
    gehend
    -0.51
    IBLIO
    -0.51
    adeloupe
    -0.51
     față
    -0.50
    POSITIVE LOGITS
     among
    0.81
    oneof
    0.79
    among
    0.69
     أحد
    0.67
     amongst
    0.66
     Among
    0.65
     AMONG
    0.62
     parmi
    0.62
    GEBURTSDATUM
    0.61
    Among
    0.60
    Activations Density 0.149%

    No Known Activations