© 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. 16-GEMMASCOPE-RES-16K
    11. 3450
    Prev
    Next
    INDEX
    Explanations

    elements that are part of a structured data format, specifically focusing on key-value pairs and attributes within lists and objects

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

    JSON-like data structures

    np_acts-logits-general · gemini-2.0-flash

    key-value assignments

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    FormTagHelper
    -0.56
     BorderLayout
    -0.55
     whichever
    -0.54
    cony
    -0.52
    DataMember
    -0.50
    ControllerAdvice
    -0.50
    odb
    -0.50
    IndentedString
    -0.49
     '<?
    -0.48
     cannes
    -0.47
    POSITIVE LOGITS
    migrationBuilder
    0.67
    InlineData
    0.64
    "]="
    0.63
    featureID
    0.62
     joaat
    0.59
     estekak
    0.59
    ']='
    0.55
    Ārējās
    0.54
    omány
    0.51
     насељу
    0.50
    Activations Density 1.544%

    No Known Activations