© 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. 22-GEMMASCOPE-RES-16K
    11. 9081
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to programming concepts

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

    Code loops ("for", "while", "loop")

    np_acts-logits-general · gemini-2.0-flash

    programming loop structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ђа
    -0.53
    UnknownFields
    -0.52
    OGND
    -0.51
    eradish
    -0.50
    Portail
    -0.49
     TextInputType
    -0.48
     syringe
    -0.47
     виправивши
    -0.47
    esModule
    -0.46
    GIVEREF
    -0.46
    POSITIVE LOGITS
     loop
    1.33
    loop
    1.19
     Loop
    1.12
     loops
    1.08
    Loop
    1.07
    loops
    1.00
     Loops
    0.99
     LOOP
    0.95
     looping
    0.94
     while
    0.94
    Activations Density 0.730%

    No Known Activations