Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 80253
    Prev
    Next
    INDEX
    Explanations

    specific identifiers and queries related to online data or content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    iſten
    -0.59
    iſter
    -0.56
    ésultats
    -0.55
     $_(
    -0.54
     ſind
    -0.54
    iſen
    -0.54
    ſſung
    -0.52
    imachinery
    -0.51
    AddTagHelper
    -0.50
    itness
    -0.50
    POSITIVE LOGITS
    RegressionTest
    0.60
    enumi
    0.43
     betweenstory
    0.41
    enumii
    0.40
    SpringRunner
    0.39
    TabIndex
    0.37
     because
    0.37
    URLException
    0.37
     souhaitent
    0.36
    TypedDataSet
    0.35
    Activations Density 0.052%

    No Known Activations