© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 10834
    Prev
    Next
    INDEX
    Explanations

    terminologies and functions related to file handling and ZIP operations in programming

    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
    存于互联网档案馆
    -0.80
    PerformLayout
    -0.79
    esModule
    -0.77
    onAttach
    -0.76
     JpaRepository
    -0.75
    Hozzáférés
    -0.74
    脚注の使い方
    -0.71
    ruptedException
    -0.69
    hydrates
    -0.69
    LookAnd
    -0.68
    POSITIVE LOGITS
    excel
    0.70
    Excel
    0.70
     Excel
    0.57
     zipfile
    0.57
    Xls
    0.55
    csv
    0.54
     EXCEL
    0.54
    Mail
    0.53
     excel
    0.51
     full
    0.51
    Activations Density 1.053%

    No Known Activations