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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 73437
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to study design and methodologies

    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
     ExecuteAsync
    -0.54
    principalColumn
    -0.53
    tangentMode
    -0.52
    EndGlobalSection
    -0.51
    UnknownFieldSet
    -0.51
    tonode
    -0.51
     yyr
    -0.50
    windowFixed
    -0.50
    tisan
    -0.46
    INCREF
    -0.45
    POSITIVE LOGITS
    今回の
    0.45
    今回
    0.42
     égard
    0.41
     this
    0.41
    此次
    0.41
    Wpf
    0.38
     данного
    0.37
    lijck
    0.36
    本次
    0.36
    łop
    0.35
    Activations Density 0.154%

    No Known Activations