© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 8826
    Prev
    Next
    INDEX
    Explanations

    terms related to matrix properties and structural elements in programming

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

    Code snippets involving coordinates or matrices

    np_acts-logits-general · gemini-2.0-flash

    technical terms and code snippets

    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
     rather
    -0.49
     latter
    -0.49
     either
    -0.45
     Rather
    -0.45
     Either
    -0.45
     themselves
    -0.44
    themselves
    -0.44
     aceea
    -0.43
    FormTagHelper
    -0.43
    Vidite
    -0.43
    POSITIVE LOGITS
    tagHelperRunner
    0.95
    openzeppelin
    0.85
    TagMode
    0.79
     AssemblyTitle
    0.76
     typelib
    0.74
     ComVisible
    0.72
     lenker
    0.68
    principalColumn
    0.68
     Offisielt
    0.66
     defaultstate
    0.66
    Activations Density 0.775%

    No Known Activations