Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 8453
    Prev
    Next
    INDEX
    Explanations

    code structure and elements related to data packing and storage in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
    TestingModule
    -0.53
    ülé
    -0.48
    ủ
    -0.47
     corona
    -0.46
    ทธิ
    -0.46
     ***!
    -0.45
     بالت
    -0.44
     stiller
    -0.43
    ProductService
    -0.42
     huom
    -0.41
    POSITIVE LOGITS
     float
    1.03
     boolean
    1.00
     bool
    0.96
     integer
    0.94
     int
    0.93
    boolean
    0.86
     Boolean
    0.84
     double
    0.84
    float
    0.83
     string
    0.82
    Activations Density 0.703%

    No Known Activations