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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 4883
    Prev
    Next
    INDEX
    Explanations

    code-related syntax elements and structure, particularly focusing on variables and mathematical calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    SBATCH
    -0.52
     yyr
    -0.51
    BufferException
    -0.50
    omotor
    -0.49
    sidemargin
    -0.48
     PublicKey
    -0.44
     jadx
    -0.43
     dri
    -0.43
    muscular
    -0.43
    理石
    -0.43
    POSITIVE LOGITS
    PreferredItem
    0.45
    umumkan
    0.42
    MessageTagHelper
    0.40
     TextAppearance
    0.40
    RTGC
    0.40
     vandens
    0.38
    KommentareTeilen
    0.37
     istrinya
    0.36
     vodu
    0.36
     segi
    0.36
    Activations Density 0.796%

    No Known Activations