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. 272
    Prev
    Next
    INDEX
    Explanations

    queries about prime factors of numbers

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

    mathematical operations and expressions involving prime factors, listing primes, and solving math problems.

    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
    enumii
    -0.66
    MLLoader
    -0.57
     invokingState
    -0.56
    OGND
    -0.54
    EndContext
    -0.51
    UnusedPrivate
    -0.51
    isContained
    -0.50
    AddHtmlAttribute
    -0.49
    centred
    -0.48
    səhifə
    -0.46
    POSITIVE LOGITS
     factors
    0.38
    Przypisy
    0.33
    Verwaltung
    0.32
    ļi
    0.32
     huella
    0.32
     оригіналу
    0.32
    findOrFail
    0.31
     thở
    0.31
     analysis
    0.30
     bugs
    0.30
    Activations Density 1.030%

    No Known Activations