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. 10594
    Prev
    Next
    INDEX
    Explanations

    programming-related data types and variable declarations

    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
     itſelf
    -1.07
     myſelf
    -0.99
     Efq
    -0.98
     iſt
    -0.88
     ſever
    -0.87
     faſt
    -0.87
     raiſ
    -0.87
     photolibrary
    -0.84
    ſelf
    -0.82
     themſelves
    -0.82
    POSITIVE LOGITS
     int
    1.69
    int
    1.09
     Int
    0.93
    Int
    0.79
     INT
    0.75
    INT
    0.71
    addComponent
    0.67
     "./
    0.57
     bool
    0.56
    poons
    0.54
    Activations Density 0.022%

    No Known Activations