© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4225
    Prev
    Next
    INDEX
    Explanations

    code related to file handling and reading or writing to files in Python

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    File opening and reading operations

    np_acts-logits-general · gemini-2.0-flash

    opening files and streams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CWE
    -0.60
    脚注の使い方
    -0.58
    quartered
    -0.57
    youts
    -0.56
    राम
    -0.55
     pinulongan
    -0.54
    onViewCreated
    -0.53
    Geplaatst
    -0.53
     resor
    -0.52
    vaig
    -0.51
    POSITIVE LOGITS
     fopen
    1.12
     opened
    1.10
     open
    1.07
    open
    1.01
    fopen
    0.95
     opening
    0.95
     ouvert
    0.93
     ouvrir
    0.88
     OPEN
    0.87
    opened
    0.87
    Activations Density 0.256%

    No Known Activations