© 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. 7-GEMMASCOPE-RES-16K
    11. 9008
    Prev
    Next
    INDEX
    Explanations

    references to various types of constructors in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Geplaatst
    -0.78
     springfox
    -0.70
    ">';
    -0.68
    Varint
    -0.67
     transfieras
    -0.64
    tinyos
    -0.62
    +#+#
    -0.61
    InvalidProtocol
    -0.59
    LEADING
    -0.59
     незавершена
    -0.59
    POSITIVE LOGITS
    constructor
    2.01
     constructor
    1.41
     Constructor
    1.06
    Constructor
    1.02
     constructors
    0.92
     initComponents
    0.88
    STRUCTOR
    0.74
    Constructors
    0.71
    reportWebVitals
    0.71
    ingale
    0.68
    Activations Density 0.013%

    No Known Activations