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. 8542
    Prev
    Next
    INDEX
    Explanations

    references to the name "Bel" or variations of it

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

    starting with "Bel" or "Bell"

    np_acts-logits-general · gemini-2.0-flash

    starts with Bel

    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
    SourceChecksum
    -0.88
    RegressionTest
    -0.82
    tagHelperRunner
    -0.80
    ukone
    -0.76
    DockStyle
    -0.70
    StructEnd
    -0.68
    Derbyniad
    -0.68
    참고
    -0.67
    IsMutable
    -0.66
    :][
    -0.65
    POSITIVE LOGITS
     BEL
    1.20
     Bel
    1.14
    Bel
    1.00
     bel
    0.96
    BEL
    0.85
    bel
    0.79
     Belmont
    0.76
     Belg
    0.71
     Belo
    0.68
     BELL
    0.67
    Activations Density 0.071%

    No Known Activations