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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 302
    Prev
    Next
    INDEX
    Explanations

    numerical data related to economics and finance

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

    financial and economic data points, like monetary values, numbers, and statistical information.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    parsedMessage
    -0.67
     initComponents
    -0.48
     Walkover
    -0.47
    السكان
    -0.47
     linkovi
    -0.46
    ⤒
    -0.45
     whither
    -0.44
     restTemplate
    -0.43
    arakhand
    -0.43
    曖昧さ回避
    -0.42
    POSITIVE LOGITS
    bloomberg
    0.55
    Bloomberg
    0.54
     Bloomberg
    0.52
     snippetHide
    0.46
     الحره
    0.45
    ANTLR
    0.40
    الدراسه
    0.40
    comune
    0.39
    Dimensioni
    0.38
    SPATH
    0.38
    Activations Density 0.028%

    No Known Activations