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. 122825
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical specifications and operational procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Technical terminology embedded in instructional or scientific text, often representing key components, actions, or processes within specialized domains.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
     AssemblyCulture
    -0.57
    хьтан
    -0.56
    Enllaces
    -0.56
    RegressionTest
    -0.55
    LabelTagHelper
    -0.54
    Искәрмәләр
    -0.54
    __(/*!
    -0.52
     încă
    -0.52
     barbati
    -0.51
    참고
    -0.49
    POSITIVE LOGITS
    WriteHeader
    0.35
     тран
    0.34
    ped
    0.32
     recording
    0.32
    Recording
    0.31
    int
    0.30
     recorded
    0.30
    tab
    0.29
    bir
    0.29
     Sun
    0.28
    Activations Density 0.269%

    No Known Activations