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. 40839
    Prev
    Next
    INDEX
    Explanations

    sections that provide background information or context

    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
     resultList
    -0.44
    GIVEREF
    -0.43
     rate
    -0.40
    anasia
    -0.40
     Iterator
    -0.40
    엇
    -0.38
    putchar
    -0.37
     free
    -0.37
     exclusive
    -0.37
     raste
    -0.37
    POSITIVE LOGITS
    Background
    0.84
    BACKGROUND
    0.81
     Background
    0.79
     Hintergrund
    0.79
     background
    0.78
    Hintergrund
    0.78
     BACKGROUND
    0.77
     backstory
    0.73
    背景
    0.69
     BoxDecoration
    0.69
    Activations Density 0.043%

    No Known Activations