© 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-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 1870
    Prev
    Next
    INDEX
    Explanations

    occurrences of the suffix "ou" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteTagHelper
    -0.83
    Abitanti
    -0.61
    Kira
    -0.59
     Gale
    -0.58
    Becker
    -0.57
     chiffre
    -0.57
     Kira
    -0.56
     начи
    -0.56
    ValueMap
    -0.55
    TemporalType
    -0.55
    POSITIVE LOGITS
    ou
    2.30
    OU
    1.95
    Ou
    1.72
     Ou
    1.58
    ous
    1.51
    oug
    1.49
    hou
    1.48
    OUS
    1.47
     Sou
    1.42
     OU
    1.39
    Activations Density 0.198%

    No Known Activations