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. 18-GEMMASCOPE-RES-16K
    6. 14397
    Prev
    Next
    INDEX
    Explanations

    keywords and constructs related to programming and data structures

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

    Swift/protobuf code related to arrays and storage

    np_acts-logits-general · gemini-2.0-flash

    static var declarations

    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
    WaitGroup
    -0.68
    Tembelea
    -0.61
     kaynağından
    -0.56
    脚注の使い方
    -0.53
    MigrationBuilder
    -0.52
     pageContext
    -0.52
     mapStateToProps
    -0.51
     fisik
    -0.49
     físico
    -0.48
     /\.
    -0.48
    POSITIVE LOGITS
    migrationBuilder
    0.66
    SourceChecksum
    0.58
    SharedDtor
    0.57
     ujednoznacz
    0.55
     _$
    0.51
     autorytatywna
    0.50
    HasAnnotation
    0.50
    addCriterion
    0.49
    anyi
    0.49
     decentral
    0.48
    Activations Density 0.160%

    No Known Activations