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. 57331
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and inequalities

    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
     Anſ
    -0.71
    OGND
    -0.69
    GEBURTSDATUM
    -0.67
     Efq
    -0.65
    richTextPanel
    -0.64
     queſta
    -0.64
     Roskov
    -0.61
     Houſe
    -0.59
    RegressionTest
    -0.59
     AssemblyCompany
    -0.59
    POSITIVE LOGITS
    期刊论文
    0.51
     claimed
    0.39
     rise
    0.35
     motivated
    0.33
     intended
    0.33
     rising
    0.32
     price
    0.32
     thought
    0.31
     induced
    0.31
    といえば
    0.31
    Activations Density 0.245%

    No Known Activations