© 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. 6215
    Prev
    Next
    INDEX
    Explanations

    syntax related to object-oriented programming and function definitions

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

    Code, often related to generic classes or databases

    np_acts-logits-general · gemini-2.0-flash

    tokens starting with p or m

    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
     nakalista
    -1.06
     Audiodateien
    -1.00
    principalTable
    -0.92
    ViewFeatures
    -0.91
     дописавши
    -0.91
     <=",
    -0.90
    SequentialGroup
    -0.90
    ViewImports
    -0.88
     <>",
    -0.87
    URLException
    -0.85
    POSITIVE LOGITS
    First
    0.54
    AS
    0.52
    N
    0.52
    New
    0.51
     First
    0.50
    Base
    0.49
     universal
    0.49
     temporary
    0.49
    My
    0.49
    No
    0.48
    Activations Density 0.297%

    No Known Activations