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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1860
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods and the associated formatting in a coding context

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

    File paths and code elements

    np_acts-logits-general · gemini-2.0-flash

    XML color/drawable attributes

    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
     propOrder
    -0.92
     AssemblyProduct
    -0.90
    GEBURTSDATUM
    -0.81
    AndEndTag
    -0.81
     NSCoder
    -0.80
    HasForeignKey
    -0.76
    __':
    -0.73
    ViewImports
    -0.73
    MockBean
    -0.68
     endwhile
    -0.68
    POSITIVE LOGITS
    Autoritní
    0.60
     eduardo
    0.57
     Greenland
    0.54
     RAS
    0.53
     Dirichlet
    0.53
     Gestalt
    0.52
     Vantage
    0.52
     Traction
    0.52
     Erb
    0.51
     pleaſure
    0.51
    Activations Density 0.002%

    No Known Activations