Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 11091
    Prev
    Next
    INDEX
    Explanations

    references to the word "one" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     насељу
    -1.10
     mergeFrom
    -0.86
    ScopeManager
    -0.80
    )");
    
    -0.79
    CrossRef
    -0.75
    "):
    
    -0.75
     AssemblyVersion
    -0.75
     kater
    -0.72
    featureID
    -0.72
    ();)
    -0.71
    POSITIVE LOGITS
    One
    0.99
     One
    0.98
    OnePlus
    0.86
     ONE
    0.86
    ONE
    0.82
     Oneida
    0.78
    one
    0.77
     hundred
    0.76
    ワン
    0.73
     OneDrive
    0.71
    Activations Density 0.148%

    No Known Activations