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. 20-GEMMASCOPE-RES-16K
    6. 13073
    Prev
    Next
    INDEX
    Explanations

    numerical values and specific legal references related to court cases

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

    Legal case numbers

    np_acts-logits-general · gemini-2.0-flash

    legal citations and formal language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Infórmanos
    -0.69
    تقاوى
    -0.68
    TypedDataSet
    -0.65
    WriteTagHelper
    -0.64
    adaptiveStyles
    -0.61
    iſen
    -0.61
    RegistryLite
    -0.60
    verifyException
    -0.60
     iprot
    -0.59
    majánló
    -0.59
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.45
    商品説明
    0.41
    XmlAccessType
    0.38
    ">//
    0.36
    ADELPHIA
    0.32
     internetowa
    0.32
    indelijk
    0.32
    ebaran
    0.31
     GALERÍA
    0.31
     ''}
    0.29
    Activations Density 0.127%

    No Known Activations