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. 20-GEMMASCOPE-RES-16K
    6. 14544
    Prev
    Next
    INDEX
    Explanations

    references to debugging processes and tools

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

    Debugging or diagnostics

    np_acts-logits-general · gemini-2.0-flash

    debugging code

    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
    upol
    -0.54
    Composable
    -0.51
    likon
    -0.48
    決め
    -0.47
     reseñas
    -0.46
     Heard
    -0.44
    skal
    -0.43
     NIOS
    -0.42
    ypeł
    -0.42
    tilor
    -0.42
    POSITIVE LOGITS
     debug
    1.64
     debugging
    1.59
     Debug
    1.40
    debug
    1.39
     Debugging
    1.37
    Debug
    1.30
    debugging
    1.28
     debugger
    1.28
     diagnostic
    1.27
     debu
    1.24
    Activations Density 0.597%

    No Known Activations