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. 134
    Prev
    Next
    INDEX
    Explanations

    technical and numerical specifications related to various subjects

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

    numerical data, including years, dates, and statistical figures.

    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
    GEBURTSDATUM
    -0.82
     propOrder
    -0.80
    parsedMessage
    -0.67
    elemField
    -0.64
    LookAnd
    -0.64
     pinulongan
    -0.62
     beginnetje
    -0.62
    évaluateur
    -0.62
    RenderAtEndOf
    -0.61
    __(/*!
    -0.59
    POSITIVE LOGITS
    ibatis
    0.43
     становника
    0.38
    oredCriteria
    0.36
     AppCompatTheme
    0.30
     wzgl
    0.29
    addTask
    0.29
    gonic
    0.29
     amantes
    0.29
    Clik
    0.28
    rítica
    0.27
    Activations Density 0.689%

    No Known Activations