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. 6485
    Prev
    Next
    INDEX
    Explanations

    instances of cutting off in driving interactions

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

    traffic or driving

    np_acts-logits-general · gemini-2.0-flash

    driving and traffic

    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
    GOTREF
    -0.40
     חיצוניים
    -0.40
     ivelany
    -0.39
     Grä
    -0.38
    embatan
    -0.38
     getPost
    -0.38
    Aiheesta
    -0.38
    OGND
    -0.37
     grá
    -0.37
     Cliquez
    -0.37
    POSITIVE LOGITS
     lane
    0.57
    ंदीखरीदारी
    0.56
     betweenstory
    0.55
     traffic
    0.47
    PMailer
    0.45
     lanes
    0.45
    ApiModel
    0.43
     Traffic
    0.42
    ❋
    0.42
     div
    0.42
    Activations Density 0.188%

    No Known Activations