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-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15937
    Prev
    Next
    INDEX
    Explanations

    phrases related to pricing and customer support in a commercial context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    after certain verbs, adjectives, or nouns

    np_acts-logits-general · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quizá
    -0.45
     chewy
    -0.43
     informée
    -0.43
     Woods
    -0.42
    ētu
    -0.42
     definitivo
    -0.41
     défis
    -0.41
    pegno
    -0.41
     grassland
    -0.40
     Ruang
    -0.40
    POSITIVE LOGITS
    principalColumn
    0.54
    BufferException
    0.53
    $_['
    0.48
     InputDecoration
    0.46
    تقاوى
    0.46
     analogues
    0.43
    ))).
    0.43
    چنین
    0.43
     berken
    0.43
     :)))
    0.43
    Activations Density 0.061%

    No Known Activations