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. 20-GEMMASCOPE-RES-16K
    6. 3361
    Prev
    Next
    INDEX
    Explanations

    terms related to fixing or repairing issues

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

    about fixing or repairing

    np_acts-logits-general · gemini-2.0-flash

    fixing and repairing issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.87
     EconPapers
    -0.87
     CreateTagHelper
    -0.86
     propOrder
    -0.85
    GraphicsUnit
    -0.84
     مرئيه
    -0.84
    rungsseite
    -0.84
     AssemblyProduct
    -0.82
    complexContent
    -0.81
    GEBURTSDATUM
    -0.80
    POSITIVE LOGITS
    Fixes
    0.66
     damaged
    0.66
    Patches
    0.65
     patching
    0.64
    Patch
    0.63
     patches
    0.63
     Patch
    0.63
    fixes
    0.61
     repairs
    0.61
     fixes
    0.61
    Activations Density 0.129%

    No Known Activations