© 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. 16-GEMMASCOPE-RES-16K
    11. 4809
    Prev
    Next
    INDEX
    Explanations

    function calls and their return structures within code

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

    Code snippets and programming terms

    np_acts-logits-general · gemini-2.0-flash

    async state/promise operations

    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
    تقاوى
    -0.99
    ConstraintMaker
    -0.93
     Roskov
    -0.91
    SourceChecksum
    -0.86
     Chwiliwch
    -0.85
    richTextPanel
    -0.85
    IndentedString
    -0.84
    MessageTagHelper
    -0.83
     AssemblyProduct
    -0.82
    ьаж
    -0.81
    POSITIVE LOGITS
    furt
    0.43
    console
    0.42
     Brind
    0.42
    yski
    0.40
     brind
    0.40
    plained
    0.40
     общем
    0.40
     among
    0.39
     것이다
    0.39
    oltre
    0.39
    Activations Density 0.055%

    No Known Activations