© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 8763
    Prev
    Next
    INDEX
    Explanations

    the preposition "of" with high frequency in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     faſt
    -0.96
     ſta
    -0.93
     ſche
    -0.89
     pleaſure
    -0.86
     juſ
    -0.84
     raiſ
    -0.82
     purpoſe
    -0.82
    ſelf
    -0.82
     ſever
    -0.81
     ſte
    -0.81
    POSITIVE LOGITS
     of
    2.69
     Of
    1.40
     OF
    1.27
    of
    1.26
    Of
    1.20
     của
    1.13
    ของ
    1.06
     של
    0.90
    オブ
    0.87
     ofthe
    0.84
    Activations Density 1.600%

    No Known Activations