© 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. 24-GEMMASCOPE-RES-16K
    11. 12463
    Prev
    Next
    INDEX
    Explanations

    instances of new data structure initializations, particularly lists and maps

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

    Java collections: ArrayList, HashMap, HashSet

    np_acts-logits-general · gemini-2.0-flash

    Java collection initialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __(/*!
    -0.65
    signol
    -0.58
    enosis
    -0.56
     africain
    -0.56
     pinulongan
    -0.56
    orsese
    -0.54
     épais
    -0.54
     zabud
    -0.53
     africaine
    -0.53
     zugelassen
    -0.52
    POSITIVE LOGITS
    <>();
    0.91
    <>();
    0.77
     يتيمه
    0.60
    <>(
    0.60
     ArrayList
    0.56
    <>
    0.55
     <>
    0.53
    LElement
    0.51
    WebControls
    0.51
    umab
    0.49
    Activations Density 0.082%

    No Known Activations