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. 33-GEMMASCOPE-RES-131K
    6. 65959
    Prev
    Next
    INDEX
    Explanations

    terms related to CSS transitions and animations

    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_33/width_131k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tanleria
    -0.60
     ComVisible
    -0.51
    MLLoader
    -0.50
     CreateTagHelper
    -0.48
    دانشنامهٔ
    -0.45
    点此举报
    -0.45
     дописавши
    -0.45
    WillAppear
    -0.44
    abestanden
    -0.44
    Olvid
    -0.44
    POSITIVE LOGITS
     ease
    0.63
     linear
    0.60
     Ease
    0.49
    linear
    0.46
     cubic
    0.46
    ease
    0.45
    Ease
    0.45
    ValueStyle
    0.44
     Linear
    0.43
     binary
    0.39
    Activations Density 0.005%

    No Known Activations