© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 9636
    Prev
    Next
    INDEX
    Explanations

    function and method definitions in code

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

    Code related to lists, arrays, or matrices

    np_acts-logits-general · gemini-2.0-flash

    list indexing and structure manipulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.61
    HomeAsUpEnabled
    -0.56
    ISupport
    -0.50
    expandindo
    -0.50
    EnableWeb
    -0.48
    initComponents
    -0.48
    mbg
    -0.46
     unknownFields
    -0.46
    modelBuilder
    -0.44
    IBOutlet
    -0.44
    POSITIVE LOGITS
    ()[
    0.83
    ')[
    0.71
    '][
    0.67
    ]--;
    0.66
     firft
    0.65
    ")[
    0.64
     Савезне
    0.62
    frist
    0.62
    first
    0.60
     firſt
    0.60
    Activations Density 0.187%

    No Known Activations