© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 15704
    Prev
    Next
    INDEX
    Explanations

    function and method calls related to retrieving names and class type information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.70
    lusconi
    -0.68
     <<<<<<<<<<<<<<
    -0.68
     ComVisible
    -0.64
     Cort
    -0.64
    uxxxx
    -0.63
    IsContent
    -0.63
     تانيه
    -0.62
    Nass
    -0.61
     Trist
    -0.59
    POSITIVE LOGITS
    getName
    2.12
     getName
    1.15
    getId
    0.93
    getSimpleName
    0.76
    getClass
    0.74
    GetName
    0.72
    setName
    0.69
    LogFactory
    0.69
    getNome
    0.68
    LoggerFactory
    0.68
    Activations Density 0.029%

    No Known Activations