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
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6646
    Prev
    Next
    INDEX
    Explanations

    objects or entities involved in battles or warfare scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    يكب
    -0.57
    NameInMap
    -0.50
     podjela
    -0.48
     ویکی‌پدی
    -0.48
    Jeografia
    -0.46
     Dario
    -0.44
    strijden
    -0.43
    GIVEREF
    -0.42
     Buche
    -0.41
    bootstrapcdn
    -0.41
    POSITIVE LOGITS
     '{@
    0.45
     avoient
    0.42
    /**
    0.40
    gardens
    0.40
    出版年
    0.39
    ↹
    0.39
    fabulous
    0.39
    bitField
    0.38
     étoit
    0.37
     virš
    0.37
    Activations Density 0.575%

    No Known Activations