© 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. 20-GEMMASCOPE-RES-16K
    11. 953
    Prev
    Next
    INDEX
    Explanations

    path-related functions and operations in code

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

    `path.resolve` or `.resolve`

    np_acts-logits-general · gemini-2.0-flash

    path.resolve or filepath.Abs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transfieras
    -0.63
     EClass
    -0.63
    +#+#
    -0.60
     actionMode
    -0.59
     contextLoads
    -0.59
     newName
    -0.59
    CppCodeGen
    -0.58
    EndProject
    -0.57
    ieR
    -0.57
    NewGuid
    -0.56
    POSITIVE LOGITS
    join
    0.70
    )";
    0.58
     join
    0.57
    '},
    0.56
    `,
    0.56
     Join
    0.56
    [];
    0.56
    Join
    0.54
    '))
    0.54
    rítica
    0.50
    Activations Density 0.089%

    No Known Activations