© 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. 24-GEMMASCOPE-RES-16K
    11. 14688
    Prev
    Next
    INDEX
    Explanations

    references to system commands and imports in programming languages

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

    Code snippets using a period (.) followed by a variable

    np_acts-logits-general · gemini-2.0-flash

    system calls and operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -0.65
     CURIAM
    -0.64
    complexType
    -0.64
    THON
    -0.64
    yntaxException
    -0.62
    Diweddarwch
    -0.61
    GEBURTSDATUM
    -0.61
     cherchés
    -0.61
    ="#"><
    -0.58
    moveToFirst
    -0.58
    POSITIVE LOGITS
    hésitez
    0.50
    __(/*!
    0.48
    +#+#
    0.47
    dat
    0.45
     certaine
    0.44
    を変える
    0.44
     dibat
    0.44
     voľ
    0.43
    exit
    0.43
    cambiar
    0.42
    Activations Density 0.247%

    No Known Activations