© 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. 13215
    Prev
    Next
    INDEX
    Explanations

    specific programming syntax and structures related to function definitions and modular programming

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

    "Mod", "MO", or similar variations

    np_acts-logits-general · gemini-2.0-flash

    modulations and motives

    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
     ivelany
    -0.68
    WriteBarrier
    -0.64
     surla
    -0.61
    évaluateur
    -0.58
    OGND
    -0.57
    enerbahçe
    -0.56
     FishBase
    -0.56
    IUrlHelper
    -0.54
     Insee
    -0.54
    GraphicsUnit
    -0.54
    POSITIVE LOGITS
     Mod
    2.23
     MOD
    2.15
     mod
    2.10
     MO
    2.09
    Mod
    2.08
     Mo
    2.03
    MOD
    1.95
    mod
    1.92
    Mo
    1.88
     mo
    1.84
    Activations Density 0.388%

    No Known Activations