© 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. 21-GEMMASCOPE-RES-16K
    11. 8627
    Prev
    Next
    INDEX
    Explanations

    mathematical comparisons and inequalities involving greater than, less than, and equality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ivos
    -0.48
     negatively
    -0.48
    nhung
    -0.47
    *}[
    -0.46
     Mandi
    -0.46
    hiba
    -0.46
    ợt
    -0.46
     Mant
    -0.44
     Bux
    -0.44
     Bul
    -0.44
    POSITIVE LOGITS
     equal
    2.45
     Equal
    2.15
    equal
    2.13
     equality
    2.07
    Equal
    2.04
     EQUAL
    2.00
     equals
    1.98
     égal
    1.81
     igual
    1.78
    EQUAL
    1.75
    Activations Density 0.611%

    No Known Activations