© 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. 16-GEMMASCOPE-RES-16K
    11. 4732
    Prev
    Next
    INDEX
    Explanations

    programming language keywords related to function and variable definitions

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

    Code-related keywords or function definitions

    np_acts-logits-general · gemini-2.0-flash

    function definitions and declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.84
     tslint
    -0.84
    extAlignment
    -0.83
     Efq
    -0.81
     doubtnut
    -0.77
     mAdapter
    -0.77
     pylint
    -0.76
     MediatR
    -0.74
     Houſe
    -0.74
     Majefty
    -0.73
    POSITIVE LOGITS
    def
    0.59
    UnsafeEnabled
    0.58
     get
    0.54
    newcommand
    0.52
    <eos>
    0.51
     my
    0.49
    *
    0.48
    ↵↵↵
    0.48
     _
    0.48
    tr
    0.47
    Activations Density 0.085%

    No Known Activations