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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 684
    Prev
    Next
    INDEX
    Explanations

    legal terminology and phrases related to contract disputes and judicial proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.66
    AndEndTag
    -0.65
    TabIndex
    -0.53
    Personendaten
    -0.51
    ArrowToggle
    -0.51
    Personensuche
    -0.51
    IUrlHelper
    -0.51
     kasarigan
    -0.51
     ModelExpression
    -0.50
    ynx
    -0.49
    POSITIVE LOGITS
     reply
    0.52
     répond
    0.50
     responds
    0.49
     respond
    0.49
     replies
    0.47
     ответил
    0.46
     rispond
    0.46
     replying
    0.44
    ตอบ
    0.43
     Respond
    0.43
    Activations Density 0.701%

    No Known Activations