© 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. 4074
    Prev
    Next
    INDEX
    Explanations

    references to CUDA device operations and error handling

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

    Two-letter beginning of words

    np_acts-logits-general · gemini-2.0-flash

    conjunctions, names, or code identifiers

    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
    CloseOperation
    -0.91
    MemoryWarning
    -0.85
    UIControlState
    -0.85
    Portail
    -0.83
    IVEREF
    -0.80
    >\<^
    -0.79
     MessageBoxIcon
    -0.78
    таратура
    -0.78
    ernalia
    -0.78
    脚注の使い方
    -0.77
    POSITIVE LOGITS
     ddelweddau
    0.56
    R
    0.53
    I
    0.48
     trans
    0.45
    P
    0.45
     Auf
    0.43
    G
    0.43
    S
    0.43
     op
    0.43
    A
    0.42
    Activations Density 0.522%

    No Known Activations