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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 12734
    Prev
    Next
    INDEX
    Explanations

    mathematical terminology and operations related to equations

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

    Mathematical expressions with fractions

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions and code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SerializedName
    -0.74
    andExpect
    -0.56
     AssemblyTitle
    -0.54
    WithIOException
    -0.53
    asso
    -0.52
    RegistryLite
    -0.51
     scanner
    -0.50
     intptr
    -0.48
    ylase
    -0.47
    hradun
    -0.46
    POSITIVE LOGITS
     GenerationType
    0.75
     كومونز
    0.72
    AsUp
    0.60
     ItemStack
    0.55
    ItemLayout
    0.54
    ContextHolder
    0.54
    PyErr
    0.54
    atim
    0.53
    тивний
    0.53
    ztés
    0.52
    Activations Density 0.726%

    No Known Activations