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. 279
    Prev
    Next
    INDEX
    Explanations

    HTML tags and related syntax

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

    code-related syntax and programming language elements, particularly Git diff markers and code snippets.

    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
     is
    -0.36
     they
    -0.33
     has
    -0.32
    有
    -0.30
     staff
    -0.30
    mAdapter
    -0.30
     added
    -0.30
     Matheson
    -0.30
     means
    -0.30
     by
    -0.29
    POSITIVE LOGITS
    NameInMap
    1.13
     autorytatywna
    1.08
    httphttps
    0.96
     Италијани
    0.96
     <<<<<<<<<<<<<<
    0.92
     Савезне
    0.90
    Personendaten
    0.89
    adaptiveStyles
    0.89
    GEBURTSDATUM
    0.88
    Билгалдахарш
    0.87
    Activations Density 0.306%

    No Known Activations