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. 3622
    Prev
    Next
    INDEX
    Explanations

    elements related to programming, particularly code structures and syntax in scripts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     enemmän
    -0.42
     мәкал
    -0.42
     betrekking
    -0.42
     makkelijk
    -0.42
    ļas
    -0.41
     påvir
    -0.40
     gemakkelijk
    -0.39
     Unterscheidung
    -0.39
     moeite
    -0.39
     piemē
    -0.38
    POSITIVE LOGITS
     staff
    0.54
     camer
    0.54
    SÍ
    0.49
     lenker
    0.49
     trustees
    0.48
     inspectors
    0.47
     auditors
    0.46
     messenger
    0.46
     scouts
    0.46
     clerks
    0.45
    Activations Density 3.557%

    No Known Activations