Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 2116
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to programming and software development errors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndGlobalSection
    -0.84
    AccessorTable
    -0.82
    thâu
    -0.75
    WriteTagHelper
    -0.72
    SourceChecksum
    -0.71
    المكان
    -0.69
    principalTable
    -0.68
    ValueStyle
    -0.68
    URLException
    -0.67
    )"),
    -0.65
    POSITIVE LOGITS
    Allgeme
    0.56
    CELLANEOUS
    0.56
     rentrée
    0.50
     estimés
    0.49
    removeAttr
    0.49
     general
    0.48
    lectric
    0.48
    cellaneous
    0.48
    basic
    0.47
    /*
    0.47
    Activations Density 0.442%

    No Known Activations