© 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. 20-GEMMASCOPE-RES-16K
    11. 6977
    Prev
    Next
    INDEX
    Explanations

    comment syntax and function documentation markers in code

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

    Code comments/documentation involving methods or functions

    np_acts-logits-general · gemini-2.0-flash

    code documentation comments

    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
    PREFERRED
    -0.58
    canti
    -0.52
    riz
    -0.51
     Dalla
    -0.49
     consequent
    -0.48
     pouce
    -0.48
    mande
    -0.47
    rog
    -0.47
    jati
    -0.47
    ofe
    -0.47
    POSITIVE LOGITS
    CppMethod
    0.67
    #+#
    0.66
     function
    0.64
     función
    0.62
     helper
    0.62
     functie
    0.62
    InSection
    0.61
     recursively
    0.61
     Used
    0.61
     iprot
    0.60
    Activations Density 0.198%

    No Known Activations