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. 103188
    Prev
    Next
    INDEX
    Explanations

    modal verbs and their usage in 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
    preced
    -0.45
    ruik
    -0.42
     proven
    -0.42
     needs
    -0.42
     հղումներ
    -0.42
     leverage
    -0.41
     lever
    -0.41
     factored
    -0.41
     Sond
    -0.41
     lẫn
    -0.40
    POSITIVE LOGITS
    MockMvc
    0.48
    centralwidget
    0.48
    ciclop
    0.46
     EconPapers
    0.43
    BeginInit
    0.40
    dataclass
    0.36
     oprot
    0.35
    toplankton
    0.35
    printStackTrace
    0.35
     Afterwards
    0.35
    Activations Density 0.019%

    No Known Activations