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. 2-GEMMASCOPE-RES-16K
    6. 15223
    Prev
    Next
    INDEX
    Explanations

    function calls and methods related to list and array processing, particularly focusing on retrieval and calculation functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     старости
    -0.50
     surla
    -0.49
     calendriers
    -0.46
    neté
    -0.45
     alas
    -0.44
     Daarna
    -0.44
    mire
    -0.44
     beware
    -0.42
    нъ
    -0.42
    вання
    -0.42
    POSITIVE LOGITS
    phosa
    0.72
    expandindo
    0.71
     Chwiliwch
    0.70
    存于互联网档案馆
    0.68
    SerializeField
    0.64
    NewGuid
    0.63
    lccn
    0.63
    EDEFAULT
    0.62
    nextInt
    0.62
    fohl
    0.61
    Activations Density 0.230%

    No Known Activations