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. 7377
    Prev
    Next
    INDEX
    Explanations

    words related to societal issues and inequalities

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

    Words that appear at the ends of sentences or phrases, often preceding punctuation marks like periods or commas, representing a variety of parts of speech including pronouns, nouns, and verbs.

    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
     madura
    -0.42
     desertcart
    -0.41
    MessageOf
    -0.40
     mater
    -0.40
     Biôgrafia
    -0.37
    Matters
    -0.37
     Alkali
    -0.36
    lioz
    -0.36
     Assignee
    -0.36
     Socialist
    -0.36
    POSITIVE LOGITS
    Παραπομπές
    0.49
    Ligações
    0.49
    Története
    0.49
    typeorm
    0.48
    Izvori
    0.46
     خارجية
    0.45
    Tracce
    0.44
    hyrchwyd
    0.43
     "..\..\
    0.43
     AssemblyTitle
    0.43
    Activations Density 0.048%

    No Known Activations