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. 40773
    Prev
    Next
    INDEX
    Explanations

    functionality related to data handling and user interface components

    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
    httphttps
    -0.55
    AddTagHelper
    -0.48
     otomatig
    -0.43
    OGND
    -0.40
     katholischen
    -0.40
    stdc
    -0.39
     indistinct
    -0.39
     JpaRepository
    -0.38
    quelize
    -0.38
    ROIT
    -0.38
    POSITIVE LOGITS
    setTag
    0.68
    WithTag
    0.57
     NSCoder
    0.55
     metav
    0.50
     tag
    0.48
    ForTesting
    0.47
     tags
    0.45
    getTag
    0.44
    Geplaatst
    0.43
    Jereo
    0.42
    Activations Density 0.010%

    No Known Activations