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. 9-GEMMASCOPE-RES-16K
    6. 3602
    Prev
    Next
    INDEX
    Explanations

    phrases connected to vibrant nightlife and lively social scenes

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

    Describes something as lively and energetic

    np_acts-logits-general · gemini-2.0-flash

    vibrant and bustling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    providedIn
    -0.54
     ***!
    -0.46
    XmlAccessorType
    -0.45
    noinspection
    -0.44
    angliski
    -0.40
     تضيفلها
    -0.40
    Indented
    -0.39
     Wiktionnaire
    -0.38
    anasia
    -0.37
    ReusableCell
    -0.37
    POSITIVE LOGITS
     bustling
    0.95
     bustle
    0.91
     vibrant
    0.86
     buzzing
    0.80
     lively
    0.78
    热闹
    0.71
     buzz
    0.69
     hustle
    0.68
    buzz
    0.66
     vib
    0.65
    Activations Density 0.285%

    No Known Activations