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. 1109
    Prev
    Next
    INDEX
    Explanations

    phrases related to customization and tailoring of various products or experiences

    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
    ValueStyle
    -1.00
     propOrder
    -0.90
    />";
    -0.76
     unknownFields
    -0.75
    SerializedName
    -0.75
     GetEnumerator
    -0.74
    ManagedBean
    -0.73
     الحره
    -0.73
    يكب
    -0.73
     Савезне
    -0.72
    POSITIVE LOGITS
     customizing
    0.80
     customize
    0.79
     customization
    0.78
     tailor
    0.74
     customized
    0.73
     tailoring
    0.71
     modifying
    0.70
    customize
    0.69
     modify
    0.68
     modification
    0.67
    Activations Density 0.619%

    No Known Activations