© 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. 23-GEMMASCOPE-RES-16K
    11. 11552
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming constructs and conditions (like class definitions, conditionals, and method calls) in source code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     setPrice
    -0.63
    kháu
    -0.59
    )++;
    -0.57
     لينك
    -0.56
    новништво
    -0.55
     Trá
    -0.50
    inā
    -0.50
    ]++;
    -0.49
    minmax
    -0.48
    さい
    -0.47
    POSITIVE LOGITS
     null
    1.02
    null
    0.86
    DockStyle
    0.83
     ==
    0.80
    ==
    0.68
     !=
    0.58
    NullException
    0.55
     Pristupljeno
    0.55
    Slf
    0.55
     nulle
    0.55
    Activations Density 0.114%

    No Known Activations