Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53533
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their placement in the text

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

    mathematical expressions and Roman alphabet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓘ
    -0.43
    kope
    -0.43
    ρίς
    -0.43
    dibles
    -0.42
     yaşam
    -0.42
    cartItems
    -0.41
     Estad
    -0.41
    estes
    -0.40
    惶
    -0.40
     Editors
    -0.40
    POSITIVE LOGITS
    RegistryLite
    0.84
    الدراسه
    0.79
    migrationBuilder
    0.79
     JpaRepository
    0.76
    ReusableCell
    0.71
     createSlice
    0.66
     pinulongan
    0.65
    Chham
    0.63
    ChildScrollView
    0.63
     beginnetje
    0.62
    Activations Density 0.572%

    No Known Activations