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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 73718
    Prev
    Next
    INDEX
    Explanations

    documents written in XHTML format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    dafx
    -0.54
    比べて
    -0.50
    RTEX
    -0.48
    tslib
    -0.45
    ByVersion
    -0.44
     Zo
    -0.42
     Meter
    -0.41
     dAtA
    -0.41
     жало
    -0.41
     Methods
    -0.41
    POSITIVE LOGITS
    igshid
    1.63
     XHTML
    1.58
    imageshack
    0.98
    expandindo
    0.89
     diseñador
    0.72
     diseñadores
    0.56
    glMatrixMode
    0.53
     springfox
    0.53
    Javadoc
    0.52
     AssemblyCompany
    0.51
    Activations Density 0.000%

    No Known Activations