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 - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 7831
    Prev
    Next
    INDEX
    Explanations

    structured data or programming concepts

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

    "layout" and related UI code

    np_acts-logits-general · gemini-2.0-flash

    Android layout and code snippets

    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
     artísticas
    -0.59
     magique
    -0.57
     turísticos
    -0.55
     médicas
    -0.52
     baterías
    -0.51
    UnsafeEnabled
    -0.51
     científicas
    -0.51
    TileEntity
    -0.50
    τέ
    -0.50
     navideñas
    -0.49
    POSITIVE LOGITS
    GroupLayout
    1.07
    MigrationBuilder
    0.74
    WriteTagHelper
    0.65
     layout
    0.64
    Hentet
    0.60
    Autoritní
    0.60
     initComponents
    0.59
    Collegamenti
    0.57
    awtextra
    0.57
     cref
    0.55
    Activations Density 0.004%

    No Known Activations