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. 151
    Prev
    Next
    INDEX
    Explanations

    technical or mathematical terms, particularly related to equations and formulae

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

    mathematical and computational notation, particularly LaTeX mathematical symbols and expressions.

    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
    ViewFeatures
    -0.46
    Tikang
    -0.32
    #+#
    -0.30
    href
    -0.29
    </
    -0.28
    ↵
    -0.27
    -
    -0.26
    <
    -0.26
    2
    -0.26
    principalTable
    -0.25
    POSITIVE LOGITS
     nothwendig
    0.81
    WriteTagHelper
    0.79
     enfans
    0.73
     Verſ
    0.73
    retudo
    0.69
     Monfieur
    0.69
     stanga
    0.68
     plufieurs
    0.67
     picioare
    0.67
     Geſ
    0.66
    Activations Density 3.294%

    No Known Activations